Soil visible and near-infrared spectroscopy provides a non-destructive, rapid and low-cost approach to quantify various soil physical and chemical properties based on their reflectance in the spectral range of 400–2500 nm. With an increasing number of large-scale soil spectral libraries established across the world and new space-borne hyperspectral sensors, there is a need to explore methods to extract informative features from reflectance spectra and produce accurate soil spectroscopic models using machine learning. Features generated from regional or large-scale soil spectral data play a key role in the quantitative spectroscopic model for soil properties. The Land Use/Land Cover Area Frame Survey (LUCAS) soil library was used to explore PLS-derived components and fractal features generated from soil spectra in this study. The gradient-boosting method performed well when coupled with extracted features on the estimation of several soil properties. Transfer learning based on convolutional neural networks (CNNs) was proposed to make the model developed from laboratory data transferable for airborne hyperspectral data. The soil clay map was successfully derived using HyMap imagery and the fine-tuned CNN model developed from LUCAS mineral soils, as deep learning has the potential to learn transferable features that generalise from the source domain to target domain. The external environmental factors like the presence of vegetation restrain the application of imaging spectroscopy. The reflectance data can be transformed into a vegetation suppressed domain with a force invariance approach, the performance of which was evaluated in an agricultural area using CASI airborne hyperspectral data. However, the relationship between vegetation and acquired spectra is complicated, and more efforts should put on removing the effects of external factors to make the model transferable from one sensor to another.:Abstract I Kurzfassung III Table of Contents V List of Figures IX List of Tables XIII List of Abbreviations XV 1 Introduction 1 1.1 Motivation 1 1.2 Soil spectra from different platforms 2 1.3 Soil property quantification using spectral data 4 1.4 Feature representation of soil spectra 5 1.5 Objectives 6 1.6 Thesis structure 7 2 Combining Partial Least Squares and the Gradient-Boosting Method for Soil Property Retrieval Using Visible Near-Infrared Shortwave Infrared Spectra 9 2.1 Abstract 10 2.2 Introduction 10 2.3 Materials and methods 13 2.3.1 The LUCAS soil spectral library 13 2.3.2 Partial least squares algorithm 15 2.3.3 Gradient-Boosted Decision Trees 15 2.3.4 Calculation of relative variable importance 16 2.3.5 Assessment 17 2.4 Results 17 2.4.1 Overview of the spectral measurement 17 2.4.2 Results of PLS regression for the estimation of soil properties 19 2.4.3 Results of PLS-GBDT for the estimation of soil properties 21 2.4.4 Relative important variables derived from PLS regression and the gradient-boosting method 24 2.5 Discussion 28 2.5.1 Dimension reduction for high-dimensional soil spectra 28 2.5.2 GBDT for quantitative soil spectroscopic modelling 29 2.6 Conclusions 30 3 Quantitative Retrieval of Organic Soil Properties from Visible Near-Infrared Shortwave Infrared Spectroscopy Using Fractal-Based Feature Extraction 31 3.1 Abstract 32 3.2 Introduction 32 3.3 Materials and Methods 35 3.3.1 The LUCAS topsoil dataset 35 3.3.2 Fractal feature extraction method 37 3.3.3 Gradient-boosting regression model 37 3.3.4 Evaluation 41 3.4 Results 42 3.4.1 Fractal features for soil spectroscopy 42 3.4.2 Effects of different step and window size on extracted fractal features 45 3.4.3 Modelling soil properties with fractal features 47 3.4.3 Comparison with PLS regression 49 3.5 Discussion 51 3.5.1 The importance of fractal dimension for soil spectra 51 3.5.2 Modelling soil properties with fractal features 52 3.6 Conclusions 53 4 Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery 55 4.1 Abstract 55 4.2 Introduction 56 4.3 Materials and Methods 59 4.3.1 Datasets 59 4.3.2 Methods 62 4.3.3 Assessment 67 4.4 Results and Discussion 67 4.4.1 Interpretation of mineral and organic soils from LUCAS dataset 67 4.4.2 1D-CNN and spectral index for LUCAS soil clay content estimation 69 4.4.3 Application of transfer learning for soil clay content mapping using the pre-trained 1D-CNN model 72 4.4.4 Comparison between spectral index and transfer learning 74 4.4.5 Large-scale soil spectral library for digital soil mapping at the local scale using hyperspectral imagery 75 4.5 Conclusions 75 5 A Case Study of Forced Invariance Approach for Soil Salinity Estimation in Vegetation-Covered Terrain Using Airborne Hyperspectral Imagery 77 5.1 Abstract 78 5.2 Introduction 78 5.3 Materials and Methods 81 5.3.1 Study area of Zhangye Oasis 81 5.3.2 Data description 82 5.3.3 Methods 83 5.3.3 Model performance assessment 85 5.4 Results and Discussion 86 5.4.1 The correlation between NDVI and soil salinity 86 5.4.2 Vegetation suppression performance using the Forced Invariance Approach 86 5.4.3 Estimation of soil properties using airborne hyperspectral data 88 5.5 Conclusions 90 6 Conclusions and Outlook 93 Bibliography 97 Acknowledgements 117

Oberflächennahe Prozesse werden durch die dynamischen Eigenschaften der Bodenoberfläche besonders beeinflusst. Zwar sind die kausalen Zusammenhänge dieser Prozesse weitestgehend bekannt, doch gibt es einen Mangel an verfügbaren Datenquellen und Erhebungsmethoden, die es erlauben, die Prozesse auf unterschiedlichen Skalen zu quantifizieren. Das Ziel dieser Arbeit bestand darin, das Potential ausgewählter moderner Fernerkundungstechnologien zu bewerten, relevante Bodeneigenschaften zu quantifizieren und damit das Verständnis von oberflächennahen Prozessen in degradierten Landschaften zu verbessern. Das Studiengebiet befand sich in einer Rekultivierunglandschaft des Niederlausitzer Braunkohletagebaus Welzow-Süd. Die Größe von 4 ha ermöglichte eine umfassende, interdisziplinäre und multi-temporale Analyse der Bodeneigenschaften auf Grundlage von Fernerkundungsmethoden sowie hydrologischen und bodenkundlichen Feld- und Labormessungen. Die Quantifizierung der Bodenfeuchte als eine entscheidende Variable für Infiltrations- und Abflussprozesse war das Ziel von labor- und feldspektroskopischen Messungen sowie von hyperspektralen Flugzeugscanner-Messungen. Der hierbei entwickelte Normalized Soil Moisture Index (NSMI) wurde als optimales Quantifizierungsmodell für Oberflächen-Bodenfeuchte im Feld ermittelt. Bodenrauhigkeit wurde in hoher Präzision durch Anwendung eines stationären Laserscanners gemessen und in Form neuartiger multi-skalarer Indizes quantifiziert. Die Analyse der raum-zeitlichen Verteilungen ermöglichte die Identifizierung von Rauhigkeitsmustern, die unter dem Einfluss der Erosion im Feld entstanden. Diese Arbeit entwickelte neuartige Methoden und Indizes zur Quantifizierung von Oberflächen-Bodenfeuchte und Rauhigkeit im Feld. Für die Zukunft verspricht deren Anwendung die Entwicklung eines tieferen Verständnisses von Bodenerosionsprozessen sowie die Sammlung wertvoller Daten durch Monitoring- und Modellierungskampagnen. / Soil processes taking place in the context of erosion and land degradation are highly dependent on the properties of the surface. While the causes and effects of such processes are commonly well understood on a conceptual level, there is a lack of adequate data sources allowing for their quantification at various spatial scales. The main goal of this thesis was to assess the role of state-of-the-art remote sensing methods for the quantification of soil properties with the aim to improve the understanding of surface processes taking place in a degraded landscape. The chosen study area of 4 ha size located in a lignite mine in eastern Germany allowed for a comprehensive, interdisciplinary and multi-temporal analysis of surface properties based on remote sensing, pedological and hydrological measurements. The quantification of surface soil moisture as an important variable for infiltration and runoff processes has been the objective in laboratory and field spectroscopic experiments as well as in airborne hyperspectral measurements. The newly developed Normalized Soil Moisture Index (NSMI) was identified as the most robust quantifier for surface soil moisture in the field. Surface roughness was successfully quantified at high precision in form of novel multiscale indices derived from datasets collected with a stationary laser scanning device. The analysis of spatiotemporal roughness distributions allowed for the detection of distinct patterns that developed under the influence of soil erosion in the field. The thesis developed a set of methods and indices that successfully implement the quantification of surface soil moisture and roughness in the field. For the future, the application of these methods promises further insights into the details of soil erosion processes taking place as well as the collection of invaluable datasets to be used for soil erosion monitoring and modeling campaigns.