Die Hauptursachen für die derzeitige weltweite Krise der biologischen Vielfalt sind Lebensraumzerstörung und Übernutzung. Wir wissen jedoch nicht, wie sich diese beiden Faktoren einzeln und zusammen auf die verschiedenen Aspekte biologischer Vielfalt auswirken und wie sie sich im Laufe der Zeit verändern. Da beide Bedrohungen weit verbreitet sind, verhindern dies die Entwicklung wirksamer Schutzstrategien. Das übergeordnete Ziel dieser Arbeit war räumliche und zeitliche Veränderungsmuster der Auswirkungen von Lebensraumzerstörung und Übernutzung auf die biologische Vielfalt zu verstehen. Ich habe diese Bedrohungsgeographien mit hoher räumlicher Auflösung und über drei Jahrzehnte hinweg für verschiedene Aspekte biologischer Vielfalt untersucht: Arten, Lebensgemeinschaften und taxonomische, phylogenetische und funktionale Facetten biologischer Vielfalt. Ich konzentrierte mich auf den 1,1 Millionen km² großen Gran Chaco, den größten tropischen Trockenwald der Welt und einen globalen Entwaldungs-Hotspot. Meine Ergebnisse zeigen, dass sich im Laufe von 30 Jahren die räumlichen Auswirkungen der einzelnen Bedrohungen auf größere Gebiete ausdehnten als nur auf die abgeholzte Fläche. Dies führte zu einem Verlust an hochwertigen und sicheren Gebieten für den Jaguar, die gesamte Großsäugergemeinschaft und alle Facetten der Säugetiervielfalt. Beide Bedrohungen trugen wesentlich zum Rückgang biologischer Vielfalt bei, ihre relative Bedeutung variierte jedoch je nach Art und Facette der biologischen Vielfalt. Zudem haben die Gebiete, in denen beide Bedrohungen zusammenwirken, im Laufe der Zeit zugenommen, was den Verlust der biologischen Vielfalt wahrscheinlich noch verschlimmert hat. Diese Arbeit unterstreicht, wie wichtig es ist, die Auswirkungen mehrerer Bedrohungen im Laufe der Zeit gemeinsam zu bewerten, um den menschlichen Einfluss auf die biologische Vielfalt besser verstehen zu können und wirksame Schutzstrategien zu finden. / The main drivers of the current global biodiversity crisis are habitat destruction and overexploitation. Yet, we lack understanding of their individual and combined spatial impact on different aspects of biodiversity, and how they change over time. Because both threats are common, these knowledge gaps preclude building more effective conservation strategies. The overarching goal of this thesis was to understand how the impacts of habitat destruction and overexploitation on biodiversity change in space and over time. I assessed these geographies of threat at high spatial resolutions and over three decades for different biodiversity aspects: species, communities, and the taxonomic, phylogenetic, and functional facets of biodiversity. I focused on the 1.1 million km² Gran Chaco, the largest tropical dry forest globally, and a global deforestation hotspot. Results reveal that over 30 years, the spatial impacts of each threat expanded over larger areas than the area deforested. This resulted in widespread losses of high-quality and safe areas for the jaguar, the entire larger mammal community and for all facets of the mammalian diversity. Such declines suggest a generalized biotic impoverishment that includes the loss of species, evolutionary history, and ecological functions across much of the Chaco. Both threats contributed substantially to biodiversity declines, and their relative importance varied among species and biodiversity facets. Moreover, the areas where both threats synergize increased over time, likely exacerbating biodiversity losses. For each biodiversity aspect, I identified priority areas of safe and high-quality habitats, and hotspots of high threat impacts, which could guide more effective complementary proactive and reactive conservation strategies. This thesis highlights the importance of jointly assessing the impact of multiple threats over time to better understand the impact of humans on biodiversity and to identify effective ways to mitigate them. / Los principales factores de la actual crisis de la biodiversidad global son la destrucción del hábitat y la sobreexplotación. Sin embargo, desconocemos su impacto espacial, tanto individual como combinado, sobre los diferentes aspectos de la biodiversidad, y cómo cambian en el tiempo. Como ambas amenazas son comunes, estos vacíos de conocimiento impiden elaborar estrategias de conservación más eficaces. El objetivo general de esta tesis fue comprender cómo los impactos de la destrucción del hábitat y la sobreexplotación en la biodiversidad cambian en el espacio y en el tiempo. Evalué estas geografías de las amenazas a altas resoluciones espaciales y a lo largo de tres décadas para diferentes aspectos de la biodiversidad: especies, comunidades y las facetas taxonómica, filogenética y funcional de la biodiversidad. Me centré en el Gran Chaco, de 1,1 millones de km², el mayor bosque seco tropical del mundo y un foco global de deforestación. Los resultados revelan que, a lo largo de 30 años, los impactos espaciales de cada una de las amenazas se extendieron por areas mayores que la superficie deforestada. Esto dio lugar a pérdidas extendidas de áreas seguras y de alta calidad para el jaguar, la comunidad de mamíferos grandes y para todas las facetas de la diversidad de mamíferos. Estos declives sugieren un empobrecimiento biótico generalizado que incluye la pérdida de especies, historia evolutiva y funciones ecológicas en gran parte del Chaco. Ambas amenazas contribuyeron sustancialmente al declive de la biodiversidad, y su importancia relativa varió entre especies y facetas de la biodiversidad. Además, las áreas en las que ambas amenazas sinergizan aumentaron en el tiempo, probablemente exacerbando las pérdidas de biodiversidad. Para cada aspecto de la biodiversidad, identifiqué áreas prioritarias de hábitats seguros y de alta calidad, y focos de alto impacto de las amenazas, que podrían orientar estrategias de conservación complementarias más eficaces, tanto proactivas como reactivas. Esta tesis destaca la importancia de evaluar conjuntamente el impacto de múltiples amenazas a lo largo del tiempo para comprender mejor el impacto de los humanos en la biodiversidad e identificar vías eficaces para mitigarlas.

The most common tool to predict future changes in species range are species distribution models. These models do, however, often underestimate potential future habitat, as they do not account for phenotypic plasticity and local adaptation, although being the most important processes in the response of tree populations to rapid climate change. Here, we quantify the difference in the predictions of future range for Norway spruce, by (i) deriving a classic, occurrence-based species distribution model (OccurrenceSDM), and (ii) analysing the variation in juvenile tree height and translating this to species occurrence (TraitSDM). Making use of 32 site locations of the most comprehensive European trial series that includes 1,100 provenances of Norway spruce originating from its natural and further beyond from its largely extended, artificial distribution, we fit a universal response function to quantify growth as a function of site and provenance climate. Both the OccurrenceSDM and TraitSDM show a substantial retreat towards the northern latitudes and higher elevations (−55 and −43%, respectively, by the 2080s). However, thanks to the species’ particularly high phenotypic plasticity in juvenile height growth, the decline is delayed. The TraitSDM identifies increasing summer heat paired with decreasing water availability as the main climatic variable that restricts growth, while a prolonged frost-free period enables a longer period of active growth and therefore increasing growth potential within the restricted, remaining area. Clear signals of local adaptation to climatic clines spanning the entire range are barely detectable, as they are disguised by a latitudinal cline. This cline strongly reflects population differentiation for the Baltic domain, but fails to capture the high phenotypic variation associated to the geographic heterogeneity in the Central European mountain ranges paired with the species history of postglacial migration. Still the model is used to provide recommendations of optimal provenance choice for future climate conditions. In essence, assisted migration may not decrease the predicted range decline of Norway spruce, but may help to capitalize on potential opportunities for increased growth associated with warmer climates.

Urgent scientifically-informed action is needed to stabilise the Earth System amidst anthropogenic climate change. Particularly, the notable transgression of the ‘biosphere integrity’ Planetary Boundary needs to be addressed. Modern Earth System Models struggle to accurately represent regional to local-scale climate features and biodiversity aspects. Recent developments allow to tackle these issues using Artificial Intelligence. This dissertation focuses on two main aspects: (i) deriving high spatio-temporal resolution climate data from coarser models; and (ii) integrating high-temporal-resolution climate data into Species Distribution Models. Three specific objectives were defined: Obj1 Improving Perfect Prognosis – Statistical Downscaling methods through modern Deep Learning algorithms. Obj2 Downscaling a high-resolution multivariate climate ensemble. Obj3 Employ the resulting dataset to improve Species Distribution Models’ projections. The objectives are connected to the three articles that support this cumulative dissertation. Its scope is limited to the Free State of Saxony, Germany, where local high-resolution climate data and high-quality observations of endangered vascular plant species were employed. From a broader perspective, these efforts should contribute to the overarching goal of bridging the gap between the scales of species distribution and climate models while establishing open-source, reproducible, and scalable containerised frameworks. Recent Deep Learning algorithms were leveraged to accomplish (i). The proposed frameworks enhance previous performance of Perfect Prognosis – Statistical Downscaling approaches, while ensuring repeatability. The key near-surface variables considered are precipitation, water vapour pressure, radiation, wind speed, and, maximum, mean and minimum temperature. The assumptions that support the Perfect Prognosis approach were thoroughly examined, confirming the robustness of the methods. The downscaled ensemble exhibits a novel output resolution of daily 1 km, which can serve as input for multiple climate impact studies, especially for local-scale decision-making and in topographically complex regions. Considerable methodological implementations were proposed and thoroughly analysed to achieve (ii). Despite notable limitations, Species Distribution Models are frequently used in climate change conservation planning. Thus, recent developments in climate data resolution could improve their usefulness and reliability, which have been previously constraint to coarse temporal aggregates in the projection domain. The presented framework provides fine-grained species suitability projections and satisfactory spatio-temporal transferability, albeit worrying trends. These improved projections are a step forward towards tailored conservation efforts. Limitations of Machine Learning methods and Species Distribution Models are addressed. Substantial avenues for future improvements are thoroughly discussed. As results suggest further reduction of suitable habitats, yet another call for swift action towards low-carbon societies is made. This requires maximising climate change mitigation and adaptation measures, along with a swift transition from short-term profit-driven policies to long-term sustainable development, but primarily, a collective shift in consciousness from anthropocentric positions to ecocentric policies and societies.:Contents Declaration of conformity........................................................ I Abstract....................................................................... III Zusammenfassung.................................................................. V Resumen........................................................................ VII Acknowledgments................................................................. IX List of Figures................................................................. XV List of Tables................................................................. XIX Symbols and Acronyms........................................................... XXI I Prelude & Foundations 1 1 Introduction................................................................... 3 1.1 Motivation – Human Impact on Earth....................................... 3 1.2 Earth System Modelling and Downscaling................................... 5 1.3 Biosphere’s Response to Recent Changes................................... 8 1.4 Species Distribution Models.............................................. 9 1.5 Objectives.............................................................. 10 1.6 Scope................................................................... 10 1.7 Outline................................................................. 10 2 Methodological Basis.......................................................... 13 2.1 Introduction to Artificial Intelligence Methods......................... 13 2.1.1 Artificial Intelligence........................................... 13 2.1.2 Machine Learning.................................................. 14 2.1.3 Deep Learning..................................................... 14 2.2 Downscaling Techniques.................................................. 15 2.2.1 Dynamical Downscaling............................................. 15 2.2.2 Statistical Downscaling........................................... 15 2.2.2.1 Model Output Statistics................................... 16 2.2.2.2 Perfect Prognosis......................................... 16 2.3 Species Distribution Models: Temporal Aspects........................... 17 2.4 Computational Framework................................................. 18 2.4.1 High-Performance Computing........................................ 18 2.4.2 Containers........................................................ 18 2.5 Remarks on Reproducibility.............................................. 19 II Articles’ Synthesis 21 3 Data.......................................................................... 23 3.1 Study Area.............................................................. 23 3.2 ReKIS................................................................... 24 3.3 ERA5.................................................................... 24 3.4 CORDEX.................................................................. 24 3.5 Species Occurrences..................................................... 25 3.6 WorldClim............................................................... 26 4 Methodological Implementations................................................ 27 4.1 Advancing Statistical Downscaling....................................... 27 4.1.1 Transfer Function Calibration.................................... 27 4.1.2 Evaluation....................................................... 29 4.1.3 Repeatability.................................................... 29 4.2 Downscaling a Multivariate Ensemble..................................... 30 4.2.1 Transfer Function Adaptations.................................... 30 4.2.2 Validation....................................................... 30 4.2.3 Perfect Prognosis Assumptions Evaluation......................... 31 4.3 Integrating High-Temporal-Resolution into SDMs.......................... 32 4.3.1 Climate Data..................................................... 32 4.3.1.1 Predictor Sets.......................................... 32 4.3.1.2 Temporal Approaches..................................... 33 4.3.2 SDM Implementation............................................... 33 4.3.3 Spatio-Temporal Thinning & Trimming.............................. 33 4.3.4 Meta-analysis.................................................... 34 4.3.5 Pseudo-Reality Assessment........................................ 34 4.3.6 Spatio-Temporal Transferability.................................. 34 5 Results & Discussions......................................................... 35 5.1 Advancing Statistical Downscaling....................................... 35 5.1.1 Performance Improvement.......................................... 35 5.1.2 Repeatability.................................................... 36 5.1.3 Transfer Function Suitability.................................... 38 5.2 Downscaling a Multivariate Ensemble..................................... 39 5.2.1 Transfer Function performance.................................... 39 5.2.2 Bias-Correction.................................................. 40 5.2.3 Pseudo-Reality................................................... 42 5.2.4 Projections...................................................... 43 5.3 Integrating High-Temporal-Resolution into SDMs.......................... 45 5.3.1 Predictor Set Evaluation for H2k................................. 45 5.3.2 Temporal Approach Comparison..................................... 46 5.3.3 Spatio-Temporal Transferability.................................. 47 5.3.4 Suitability Projections.......................................... 47 III Insights 51 6 Summary....................................................................... 53 6.1 Article A1.............................................................. 53 6.2 Article A2.............................................................. 54 6.3 Article A3.............................................................. 56 7 Conclusions and Outlook....................................................... 59 References 65 Articles 81 A1 Repeatable high-resolution statistical downscaling through deep learning..... 83 A2 Downscaling CORDEX Through Deep Learning to Daily 1 km Multivariate Ensemble in Complex Terrain............................................................. 103 A3 Integrating High-Temporal-Resolution Climate Projections into Species Distribu- tion Model..................................................................... 127 / Um das Erdsystem angesichts des anthropogenen Klimawandels zu stabilisieren, sind Maßnahmen auf Basis wissenschaftlicher Erkenntnisse dringend erforderlich. Insbesondere muss die drastisch Überschreitung der planetaren Grenze ‘Integrität der Biosphäre’ angegangen werden. Bisher haben aber Modelle des Erdsystems Schwierigkeiten, regionale bis lokale Klimamerkmale und Aspekte der Biodiversität genau abzubilden. Aktuelle Entwicklungen ermöglichen es, diese Herausforderungen mithilfe von Künstlicher Intelligenz anzugehen. Diese Dissertation konzentriert sich auf zwei Hauptaspekte: (i) die Ableitung von Klimadaten mit hoher räumlicher und zeitlicher Auflösung aus groberen Modellen und (ii) die Integration von Klimadaten mit hoher zeitlicher Auflösung in Modelle zur Artverbreitung. Es wurden drei konkrete Ziele definiert: Ziel1 Verbesserung von Perfect Prognosis – Statistische Downscaling-Methoden durch moderne Deep Learning-Algorithmen Ziel2 Downscaling eines hochauflösenden multivariaten Klimaensembles Ziel3 Verwendung des resultierenden Datensatzes zur Verbesserung von Prognosen in Modellen zur Artverbreitung Diese Ziele werden in drei wissenschaftlichen Artikeln beantwortet, auf die diese kumulative Dissertation sich stützt. Der Anwendungsbereich erstreckt sich auf den Freistaat Sachsen, Deutschland, wo lokale hochauflösende Klimadaten und hochwertige Beobachtungen gefährdeter Gefäßpflanzenarten verwendet wurden. In einer breiteren Perspektive tragen diese Bemühungen dazu bei, die Kluft zwischen regionalen sowie zeitlichen Skalen der Artverbreitung und Klimamodellen zu überbrücken und gleichzeitig Open-Source-, reproduzierbare und skalierbare containerisierte Frameworks zu etablieren. Aktuelle Deep Learning-Algorithmen wurden eingesetzt, um Hauptaspekt (i) zu erreichen. Die vorgeschlagenen Frameworks verbessern die bisherige Leistung von Perfect Prognosis – Statistische Downscaling-Ansätzen und gewährleisten gleichzeitig die Wiederholbarkeit. Die wichtigsten bodennahen Variablen, die berücksichtigt werden, sind Niederschlag, Wasserdampfdruck, Strahlung, Windgeschwindigkeit sowie Maximal-, Durchschnitts- und Minimaltemperatur. Die Annahmen, die den Perfect Prognosis-Ansatz unterstützen, wurden analysiert und bestätigen die Robustheit der Methoden. Das downscaled Ensemble weist eine neuartige Auflösung von 1 km auf Tagesbasis auf, welches als Grundlage für mehrere Studien zu den Auswirkungen des Klimawandels dienen kann, insbesondere für Entscheidungsfindung auf lokaler Ebene und in topografisch komplexen Regionen. Es wurden umfassende methodische Implementierungen vorgeschlagen und analysiert, um Hauptaspekt (ii) zu erreichen. Trotz großer Einschränkungen werden Modelle zur Artverbreitung häufig in der Klimaschutzplanung eingesetzt. Daher könnten aktuelle Entwicklungen in der Klimadatenauflösung deren Nützlichkeit und Zuverlässigkeit verbessern, die bisher auf grobe zeitliche Aggregatformen im Projektionsbereich beschränkt waren. Das vorgestellte Framework bietet feingliedrige Prognosen zur Eignung von Arten und zufriedenstellende räumlich-zeitliche Übertragbarkeit, trotz besorgniserregender Trends. Diese verbesserten Prognosen sind ein Schritt in Richtung maßgeschneiderter Naturschutzmaßnahmen. Einschränkungen von Machine Learning-Methoden und Modellen zur Artverbreitung werden untersucht. Substanzielle Möglichkeiten zur zukünftigen Verbesserung werden ausführlich erörtert. Da die Ergebnisse darauf hinweisen, dass geeignete Lebensräume weiter abnehmen, wird erneut zum schnellen Handeln in Richtung kohlenstoffarmer Gesellschaften aufgerufen. Dies erfordert die Maximierung von Maßnahmen zur Bekämpfung des Klimawandels und zur Anpassung, zusammen mit einem raschen Übergang von kurzfristig Profitorientierten Politiken zu langfristiger nachhaltiger Entwicklung, aber vor allem zu einem kollektiven Bewusstseinswandel von anthropozentrischen Positionen zu ökozentrischen Politiken und Gesellschaften.:Contents Declaration of conformity........................................................ I Abstract....................................................................... III Zusammenfassung.................................................................. V Resumen........................................................................ VII Acknowledgments................................................................. IX List of Figures................................................................. XV List of Tables................................................................. XIX Symbols and Acronyms........................................................... XXI I Prelude & Foundations 1 1 Introduction................................................................... 3 1.1 Motivation – Human Impact on Earth....................................... 3 1.2 Earth System Modelling and Downscaling................................... 5 1.3 Biosphere’s Response to Recent Changes................................... 8 1.4 Species Distribution Models.............................................. 9 1.5 Objectives.............................................................. 10 1.6 Scope................................................................... 10 1.7 Outline................................................................. 10 2 Methodological Basis.......................................................... 13 2.1 Introduction to Artificial Intelligence Methods......................... 13 2.1.1 Artificial Intelligence........................................... 13 2.1.2 Machine Learning.................................................. 14 2.1.3 Deep Learning..................................................... 14 2.2 Downscaling Techniques.................................................. 15 2.2.1 Dynamical Downscaling............................................. 15 2.2.2 Statistical Downscaling........................................... 15 2.2.2.1 Model Output Statistics................................... 16 2.2.2.2 Perfect Prognosis......................................... 16 2.3 Species Distribution Models: Temporal Aspects........................... 17 2.4 Computational Framework................................................. 18 2.4.1 High-Performance Computing........................................ 18 2.4.2 Containers........................................................ 18 2.5 Remarks on Reproducibility.............................................. 19 II Articles’ Synthesis 21 3 Data.......................................................................... 23 3.1 Study Area.............................................................. 23 3.2 ReKIS................................................................... 24 3.3 ERA5.................................................................... 24 3.4 CORDEX.................................................................. 24 3.5 Species Occurrences..................................................... 25 3.6 WorldClim............................................................... 26 4 Methodological Implementations................................................ 27 4.1 Advancing Statistical Downscaling....................................... 27 4.1.1 Transfer Function Calibration.................................... 27 4.1.2 Evaluation....................................................... 29 4.1.3 Repeatability.................................................... 29 4.2 Downscaling a Multivariate Ensemble..................................... 30 4.2.1 Transfer Function Adaptations.................................... 30 4.2.2 Validation....................................................... 30 4.2.3 Perfect Prognosis Assumptions Evaluation......................... 31 4.3 Integrating High-Temporal-Resolution into SDMs.......................... 32 4.3.1 Climate Data..................................................... 32 4.3.1.1 Predictor Sets.......................................... 32 4.3.1.2 Temporal Approaches..................................... 33 4.3.2 SDM Implementation............................................... 33 4.3.3 Spatio-Temporal Thinning & Trimming.............................. 33 4.3.4 Meta-analysis.................................................... 34 4.3.5 Pseudo-Reality Assessment........................................ 34 4.3.6 Spatio-Temporal Transferability.................................. 34 5 Results & Discussions......................................................... 35 5.1 Advancing Statistical Downscaling....................................... 35 5.1.1 Performance Improvement.......................................... 35 5.1.2 Repeatability.................................................... 36 5.1.3 Transfer Function Suitability.................................... 38 5.2 Downscaling a Multivariate Ensemble..................................... 39 5.2.1 Transfer Function performance.................................... 39 5.2.2 Bias-Correction.................................................. 40 5.2.3 Pseudo-Reality................................................... 42 5.2.4 Projections...................................................... 43 5.3 Integrating High-Temporal-Resolution into SDMs.......................... 45 5.3.1 Predictor Set Evaluation for H2k................................. 45 5.3.2 Temporal Approach Comparison..................................... 46 5.3.3 Spatio-Temporal Transferability.................................. 47 5.3.4 Suitability Projections.......................................... 47 III Insights 51 6 Summary....................................................................... 53 6.1 Article A1.............................................................. 53 6.2 Article A2.............................................................. 54 6.3 Article A3.............................................................. 56 7 Conclusions and Outlook....................................................... 59 References 65 Articles 81 A1 Repeatable high-resolution statistical downscaling through deep learning..... 83 A2 Downscaling CORDEX Through Deep Learning to Daily 1 km Multivariate Ensemble in Complex Terrain............................................................. 103 A3 Integrating High-Temporal-Resolution Climate Projections into Species Distribu- tion Model..................................................................... 127 / Acción urgente científicamente informada es necesaria para estabilizar el sistema terrestre en medio del cambio climático antropogénico. En particular, la notable transgresión del límite planetario de ’integridad de la biosfera’ debe abordarse. Los modernos modelos del sistema terrestre tienen dificultades para representar con precisión las características climáticas a escala regional y local, así como los aspectos de la biodiversidad. Desarrollos recientes permiten abordar estos problemas mediante la inteligencia artificial. Esta disertación se enfoca en dos aspectos principales: (i) derivar datos climáticos de alta resolución espacio-temporal a partir de modelos más gruesos; y (ii) integrar datos climáticos de alta resolución temporal en modelos de distribución de especies. Se definieron tres objetivos específicos: Obj1 Mejorar los métodos de pronóstico perfecto – reducción de escala estadística mediante algoritmos modernos de aprendizaje profundo. Obj2 Generar un conjunto climático multivariado de alta resolución. Obj3 Emplear el conjunto de datos resultante para mejorar las proyecciones de los modelos de distribución de especies. Los objetivos están vinculados a los tres artículos que respaldan esta disertación acumulativa. Su alcance se limita al Estado Libre de Sajonia, Alemania, donde se emplearon datos climáticos locales de alta resolución y observaciones de alta calidad de especies de plantas vasculares en peligro de extinción. Desde una perspectiva más amplia, estos esfuerzos deberían contribuir a la meta general de cerrar la brecha entre las escalas de la distribución de especies y los modelos climáticos, mientras que se establecen marcos de trabajo contenedorizados de código abierto, reproducibles y escalables. Algoritmos recientes de aprendizaje profundo fueron aprovechados para lograr (i). Los marcos de trabajo propuestos mejoran el rendimiento previo de los métodos de pronóstico perfecto – reducción de escala estadística, al tiempo que garantizan la repetibilidad. Las variables clave de la superficie cercana consideradas son precipitación, presión de vapor de agua, radiación, velocidad del viento, así como la temperatura máxima, media y mínima. Se examinaron meticulosamente las suposiciones que respaldan el método de pronóstico perfecto, confirmando la robustez de las propuestas. El conjunto reducido de escala exhibe una novedosa resolución diaria de 1 km, el cual puede servir como insumo para múltiples estudios de impacto climático, especialmente para la toma de decisiones a nivel local y en regiones topográficamente complejas. Se propusieron y analizaron minuciosamente considerables implementaciones metodológicas para lograr (ii). A pesar de sus notables limitaciones, los modelos de distribución de especies son utilizados con frecuencia en la planificación de la conservación debido al cambio climático. Por lo tanto, los desarrollos recientes en la resolución de datos climáticos podrían mejorar su utilidad y confiabilidad, ya que antes se limitaban a agregados temporales gruesos en el caso de las proyecciones. El marco de trabajo presentado proporciona proyecciones de idoneidad de especies detalladas y una transferibilidad espacio-temporal satisfactoria, aunque con tendencias preocupantes. Estas proyecciones mejoradas son un paso adelante en los esfuerzos de conservación a la medida. Se abordan las limitaciones de los métodos de aprendizaje automático y de los modelos de distribución de especies. Se discuten a fondo posibilidades sustanciales para futuras mejoras. Dado que los resultados sugieren una mayor reducción de hábitats adecuados, se hace otro llamado a la acción rápida hacia sociedades bajas en carbono. Esto requiere maximizar las medidas de mitigación y adaptación al cambio climático, junto con una transición rápida de políticas orientadas a beneficios a corto plazo hacia un desarrollo sostenible a largo plazo, pero principalmente, un cambio colectivo de conciencia, desde posiciones antropocéntricas hacia políticas y sociedades ecocéntricas.:Contents Declaration of conformity........................................................ I Abstract....................................................................... III Zusammenfassung.................................................................. V Resumen........................................................................ VII Acknowledgments................................................................. IX List of Figures................................................................. XV List of Tables................................................................. XIX Symbols and Acronyms........................................................... XXI I Prelude & Foundations 1 1 Introduction................................................................... 3 1.1 Motivation – Human Impact on Earth....................................... 3 1.2 Earth System Modelling and Downscaling................................... 5 1.3 Biosphere’s Response to Recent Changes................................... 8 1.4 Species Distribution Models.............................................. 9 1.5 Objectives.............................................................. 10 1.6 Scope................................................................... 10 1.7 Outline................................................................. 10 2 Methodological Basis.......................................................... 13 2.1 Introduction to Artificial Intelligence Methods......................... 13 2.1.1 Artificial Intelligence........................................... 13 2.1.2 Machine Learning.................................................. 14 2.1.3 Deep Learning..................................................... 14 2.2 Downscaling Techniques.................................................. 15 2.2.1 Dynamical Downscaling............................................. 15 2.2.2 Statistical Downscaling........................................... 15 2.2.2.1 Model Output Statistics................................... 16 2.2.2.2 Perfect Prognosis......................................... 16 2.3 Species Distribution Models: Temporal Aspects........................... 17 2.4 Computational Framework................................................. 18 2.4.1 High-Performance Computing........................................ 18 2.4.2 Containers........................................................ 18 2.5 Remarks on Reproducibility.............................................. 19 II Articles’ Synthesis 21 3 Data.......................................................................... 23 3.1 Study Area.............................................................. 23 3.2 ReKIS................................................................... 24 3.3 ERA5.................................................................... 24 3.4 CORDEX.................................................................. 24 3.5 Species Occurrences..................................................... 25 3.6 WorldClim............................................................... 26 4 Methodological Implementations................................................ 27 4.1 Advancing Statistical Downscaling....................................... 27 4.1.1 Transfer Function Calibration.................................... 27 4.1.2 Evaluation....................................................... 29 4.1.3 Repeatability.................................................... 29 4.2 Downscaling a Multivariate Ensemble..................................... 30 4.2.1 Transfer Function Adaptations.................................... 30 4.2.2 Validation....................................................... 30 4.2.3 Perfect Prognosis Assumptions Evaluation......................... 31 4.3 Integrating High-Temporal-Resolution into SDMs.......................... 32 4.3.1 Climate Data..................................................... 32 4.3.1.1 Predictor Sets.......................................... 32 4.3.1.2 Temporal Approaches..................................... 33 4.3.2 SDM Implementation............................................... 33 4.3.3 Spatio-Temporal Thinning & Trimming.............................. 33 4.3.4 Meta-analysis.................................................... 34 4.3.5 Pseudo-Reality Assessment........................................ 34 4.3.6 Spatio-Temporal Transferability.................................. 34 5 Results & Discussions......................................................... 35 5.1 Advancing Statistical Downscaling....................................... 35 5.1.1 Performance Improvement.......................................... 35 5.1.2 Repeatability.................................................... 36 5.1.3 Transfer Function Suitability.................................... 38 5.2 Downscaling a Multivariate Ensemble..................................... 39 5.2.1 Transfer Function performance.................................... 39 5.2.2 Bias-Correction.................................................. 40 5.2.3 Pseudo-Reality................................................... 42 5.2.4 Projections...................................................... 43 5.3 Integrating High-Temporal-Resolution into SDMs.......................... 45 5.3.1 Predictor Set Evaluation for H2k................................. 45 5.3.2 Temporal Approach Comparison..................................... 46 5.3.3 Spatio-Temporal Transferability.................................. 47 5.3.4 Suitability Projections.......................................... 47 III Insights 51 6 Summary....................................................................... 53 6.1 Article A1.............................................................. 53 6.2 Article A2.............................................................. 54 6.3 Article A3.............................................................. 56 7 Conclusions and Outlook....................................................... 59 References 65 Articles 81 A1 Repeatable high-resolution statistical downscaling through deep learning..... 83 A2 Downscaling CORDEX Through Deep Learning to Daily 1 km Multivariate Ensemble in Complex Terrain............................................................. 103 A3 Integrating High-Temporal-Resolution Climate Projections into Species Distribu- tion Model..................................................................... 127

Agri-environment schemes (AESs), ecological focus areas (EFAs), and organic farming are the main tools of the common agricultural policy (CAP) to counteract the dramatic decline of farmland biodiversity in Europe. However, their effectiveness is repeatedly doubted because it seems to vary when measured at the field-versus-landscape level and to depend on the regional environmental and land-use context. Understanding the heterogeneity of their effectiveness is thus crucial to developing management recommendations that maximize their efficacy. Using ensemble species distribution models and spatially explicit field-level information on crops grown, farming practice (organic/conventional), and applied AES/EFA from the Integrated Administration and Control System, we investigated the contributions of five groups of measures (buffer areas, cover crops, extensive grassland management, fallow land, and organic farming) to habitat suitability for 15 farmland bird species in the Mulde River Basin, Germany. We used a multiscale approach to identify the scale of effect of the selected measures. Using simulated land-use scenarios, we further examined how breeding habitat suitability would change if the measures were completely removed and if their adoption by farmers increased to meet conservation-informed targets. Buffer areas, fallow land, and extensive grassland were beneficial measures for most species, but cover crops and organic farming had contrasting effects across species. While different measures acted at different spatial scales, our results highlight the importance of land-use management at the landscape level—at which most measures had the strongest effect. We found that the current level of adoption of the measures delivers only modest gains in breeding habitat suitability. However, habitat suitability improved for the majority of species when the implementation of the measures was increased, suggesting that they could be effective conservation tools if higher adoption levels were reached. The heterogeneity of responses across species and spatial scales indicated that a mix of different measures, applied widely across the agricultural landscape, would likely maximize the benefits for biodiversity. This can only be achieved if the measures in the future CAP will be cooperatively designed in a regionally targeted way to improve their attractiveness for farmers and widen their uptake.

<p>Land use change constitutes a primary driving force in shaping social-ecological systems world wide, and its effects reach far beyond the directly impacted areas. Graph based landscape ecological tools have become established as a promising way to efficiently explore and analyze the complex, spatial systems dynamics of ecological networks in physical landscapes. However, little attention has been paid to making these approaches operational within ecological assessments, physical planning, and design. This thesis presents a network based, landscape-ecological tool that can be implemented for effective use by practitioners within physical planning and design, and ecological assessments related to these activities. The tool is based on an ecological profile system, a common generalized network model of the ecological infrastructure, graph theoretic metrics, and a spatially explicit, geographically defined representation, deployable in a GIS. Graph theoretic metrics and analysis techniques are able to capture the spatio-temporal dynamics of complex systems, and the generalized network model places the graph theoretic toolbox in a geographically defined landscape. This provides completely new insights for physical planning, and environmental assessment activities. The design of the model is based on the experience gained through seven real-world cases, commissioned by different governmental organizations within Stockholm County. A participatory approach was used in these case studies, involving stakeholders of different backgrounds, in which the tool proved to be flexible and effective in the communication and negotiation of indicators, targets, and impacts. In addition to successful impact predictions for alternative planning scenarios, the tool was able to highlight critical ecological structures within the landscape, both from a system-centric, and a site-centric perspective. In already being deployed and used in planning, assessments, inventories, and monitoring by several of the involved organizations, the tool has proved to effectively meet some of the challenges of application in a multidisciplinary landscape.</p>

Land use change constitutes a primary driving force in shaping social-ecological systems world wide, and its effects reach far beyond the directly impacted areas. Graph based landscape ecological tools have become established as a promising way to efficiently explore and analyze the complex, spatial systems dynamics of ecological networks in physical landscapes. However, little attention has been paid to making these approaches operational within ecological assessments, physical planning, and design. This thesis presents a network based, landscape-ecological tool that can be implemented for effective use by practitioners within physical planning and design, and ecological assessments related to these activities. The tool is based on an ecological profile system, a common generalized network model of the ecological infrastructure, graph theoretic metrics, and a spatially explicit, geographically defined representation, deployable in a GIS. Graph theoretic metrics and analysis techniques are able to capture the spatio-temporal dynamics of complex systems, and the generalized network model places the graph theoretic toolbox in a geographically defined landscape. This provides completely new insights for physical planning, and environmental assessment activities. The design of the model is based on the experience gained through seven real-world cases, commissioned by different governmental organizations within Stockholm County. A participatory approach was used in these case studies, involving stakeholders of different backgrounds, in which the tool proved to be flexible and effective in the communication and negotiation of indicators, targets, and impacts. In addition to successful impact predictions for alternative planning scenarios, the tool was able to highlight critical ecological structures within the landscape, both from a system-centric, and a site-centric perspective. In already being deployed and used in planning, assessments, inventories, and monitoring by several of the involved organizations, the tool has proved to effectively meet some of the challenges of application in a multidisciplinary landscape.

<p dir="ltr">Global forest ecosystems provide essential ecosystem services that contribute to water and climate regulation, food production, recreation, and raw materials. They also serve as crucial habitats for numerous terrestrial species of amphibians, birds, and mammals worldwide. However, recent decades have witnessed unprecedented changes in forest ecosystems due to climate change, shifts in species distribution patterns, increased planted forest areas, and various disturbances such as forest fires, insect infestations, and urbanization. These changes can have far-reaching impacts on ecological networks, human well-being, and the well-being of global forest ecosystems. To address these challenges, I present four studies to quantify forest dynamics through mapping, classification, and projection, using artificial intelligence tools in combination with a vast amount of training data. (I) I present a spatially continuous map of planted forest distribution across East Asia, produced by integrating multiple sources of planted and natural forest data. I found that China contributed 87% of the total planted forest areas in East Asia, most of which are located in the lowland tropical/subtropical regions and Sichuan Basin. I also estimated the dominant genus in each planted forest location. (II) I used continent-wide forest inventory data to compare the range shifts of forest types and their constituent tree species in North America in the past 50 years. I found that forest types shifted more than three times as fast as the average of their constituent tree species. This marked difference was attributable to a predominant positive covariance between tree species ranges and the change of species relative abundance. (III) Based on individual-level field surveys of trees and breeding birds across North America, I characterized New World wood-warbler (<i>Parulidae</i>) species richness and its potential drivers. I identified forest type as the most powerful predictor of New World wood-warbler species richness, which adds valuable evidence to the ongoing physiognomy versus composition debate among ornithologists. (IV) In the appendix, I utilized continent-wide forest inventory data from North America and South America and the combination of supervised and unsupervised machine learning algorithms to produce the first data-driven map of forest types in the Americas. I revealed the distribution of forest types, which are useful for cost-effective forest and biodiversity management and planning. Taken together, these studies provide insight into the dynamics of forest ecosystems at a large geographic scale and have implications for effective decision-making in conservation, management, and global restoration programs in the midst of ongoing global change.</p>