The population of the world is increasing exponentially each year with a large population base. Agricultural fields are facing the pressure of dealing with food insufficiency, whereas the challenges of limited resources of arable land and fresh water on the earth should be taken into account at the same time. Smart farming was born at the right time to cope with the problem and has become one of the most powerful approaches to reducing the ecological footprint of farming and improving agricultural yield. The four most important variables that impact crop yield are soil productivity, the accessibility of water, climate, and pests or diseases. This thesis emphasizes the application of chemical fertilizers to corn and disregards the impact of water, pests, and disease for the moment. In this study, three scenarios are explored deeper one by one. The only factor that varies among the three scenarios is the nitrogen amount available to the plant. Fertilizers have outstanding performance in improving the yield and quality of plants in agricultural fields, and this is the emphasis of this thesis. Compared with the fertilizer properties and characteristics of frequently used commercial fertilizers, polymer-coated urea was selected as the fertilizer in this study because the feature of nitrogen can be released into the soil slowly and in a controlled manner. Scenario 1 created an ideal condition where unlimited nitrogen was provided to the corn. Scenario 2 assumed that a fixed amount of polymer-coated urea was applied at the beginning of the sowing season only. Scenario 3 figured out an optimal yield by separating the fertilizer application at the beginning and in the middle of the growing days with the same amounts of fertilizer used in Scenario 2. The model was performed based on historical data from Oklahoma and Ottawa using IoT sensors. The simulation model generated with Python figured out that approximately the end of June to the start of July is the best time to apply the remaining fertilizer, assuming that the sowing stage starts on May 1. The percentage of polymer-coated urea applied initially was found to usually be around 10% in the tested regions. The model was used to predict the yield in Ottawa using from 40.94 g/(m^2) in Scenario 2 to 55.43 g/(m^2) in Scenario 3, achieving an outstanding increasing rate of 35.38%.

The world’s population is expected to grow to 9.6 billion by 2050. This exponential growth imposes a significant challenge on food security making the development of efficient crop production a growing concern. The traditional methods of analyzing soil and crop yield rely on manual field surveys and the use of expensive instruments. This process is not only time-consuming but also requires a team of specialists making this method of prediction expensive. Prediction of yield is an integral part of smart farming as it enables farmers to make timely informed decisions and maximize productivity while minimizing waste. Traditional statistical approaches fall short in optimizing yield prediction due to the multitude of diverse variables that influence crop production. Additionally, the interactions between these variables are non-linear which these methods fail to capture. Recent approaches in machine learning and data-driven models are better suited for handling the complexity and variability of crop yield prediction. Maize, also known as corn, is a staple crop in many countries and is used in a variety of food products, including bread, cereal, and animal feed. In 2021-2022, the total production of corn was around 1.2 billion tonnes superseding that of wheat or rice, making it an essential element of food production. With the advent of remote sensing, Unmanned aerial vehicles or UAVs are widely used to capture high-quality field images making it possible to capture minute details for better analysis of the crops. By combining spatial features, such as topography and soil type, with crop growth information, it is possible to develop a robust and accurate system for predicting crop yield. Convolutional Neural Networks (CNNs) are a type of deep neural network that has shown remarkable success in computer vision tasks, achieving state-of-the-art performance. Their ability to automatically extract features and patterns from data sets makes them highly effective in analyzing complex and high-dimensional datasets, such as drone imagery. In this research, we aim to build an effective crop yield predictor using data fusion and deep learning. We propose several Deep CNN architectures that can accurately predict corn yield before the end of the harvesting season which can aid farmers by providing them with valuable information about potential harvest outcomes, enabling them to make informed decisions regarding resource allocation. UAVs equipped with RGB (Red Green Blue) and multi-spectral cameras were scheduled to capture high-resolution images for the entire growth period of 2021 of 3 fields located in Ottawa, Ontario, where primarily corn was grown. Whereas, the ground yield data was acquired at the time of harvesting using a yield monitoring device mounted on the harvester. Several data processing techniques were employed to remove erroneous measurements and the processed data was fed to different CNN architectures, and several analyses were done on the models to highlight the best techniques/methods that lead to the most optimal performance. The final best-performing model was a 3-dimensional CNN model that can predict yield utilizing the images from the Early(June) and Mid(July) growing stages with a Mean Absolute Percentage error of 15.18% and a Root Mean Squared Error of 17.63 (Bushels Per Acre). The model trained on data from Field 1 demonstrated an average Correlation Coefficient of 0.57 between the True and Predicted yield values from Field 2 and Field 3. This research provides a direction for developing an end-to-end yield prediction model. Additionally, by leveraging the results from the experiments presented in this research, image acquisition, and computation costs can be brought down.

Smart agriculture is an increasingly popular field in which the technology of wireless sensor networks (WSN) has played a large role. Significant research has been done at Cal Poly and elsewhere to develop a computer vision (CV) and machine learning (ML) pipeline to monitor crops and accurately predict crop yield numbers. By autonomously providing farmers with this data, both time and money are saved. During the past development of a prediction pipeline, the primary focuses were CV and ML processing while a lack of attention was given to the collection of quality image data. This lack of focus in previous research presented itself as incomplete and inefficient processing models. This thesis work attempts to solve this image acquisition problem through the initial development and design of an Internet of Things (IoT) prototype network to collect consistent image data with no human interaction. The system is developed with the goals of being low-power, low-cost, autonomous, and scalable. The proposed IoT network nodes are based on the ESP32 SoC and communicate over-the-air with the gateway node via Bluetooth Low Energy (BLE). In addition to BLE, the gateway node periodically uplinks image data via Wi-Fi to a cloud server to ensure the accessibility of collected data. This research develops all functionality of the network, comprehensively characterizes the power consumption of IoT nodes, and provides battery life estimates for sensor nodes. The sensor node developed consumes a peak current of 150mA in its active state and sleeps at 162µA in its standby state. Node-to-node BLE data transmission throughput of 220kbps and node-tocloud Wi-Fi data transmission throughput of 709.5kbps is achieved. Sensor node device lifetime is estimated to be 682 days on a 6600mAh LiPo battery while acquiring five images per day. This network can be utilized by any application that requires a wireless sensor network (WSN), high data rates, low power consumption, short range communication, and large amounts of data to be transmitted at low frequency intervals.

A cause du développement du smart farming, des études sont à mener sur la distribution de l’instrumentation pour mesurer l’état hydrique du sol en vue de contrôler l’irrigation. Dans le cadre du projet IRRIS, nous réalisons un capteur d’humidité du sol intelligent. Nous allons tout d’abord réaliser le corps d’épreuve de ce capteur. Nous choisissons une mesure capacitive pour obtenir un capteur réactif malgré un coût de réalisation faible. Le corps est cylindrique pour pouvoir être inséré facilement dans le sol. Les électrodes sont réalisées par dépôt électrochimique de cuivre sur ce cylindre plastique. Nous concevons ensuite l’électronique de mesure associée à ce corps. Pour cela, nous comparons deux solutions, l’une analogique et l’autre logicielle. Puis nous assemblons notre capteur suivant deux modes, le multi capteur ou le mono capteur. Nous réalisons à cette étape la création du réseau de capteurs à l’aide de communication sans fil située dans la bande ISM 868MHz et nous la caractérisons. Enfin, nous observons les résultats de trois campagnes de mesures dans des champs cultivés pour valider le fonctionnement sur différents types de sols et de cultures. Ces travaux aboutissent donc à la création d’un capteur permettant la mesure de l’humidité du sol avec un coût réduit par rapport aux capteurs industriel déjà existant. Les expérimentations sur site montrent sa facilité d’insertion ainsi que son bon fonctionnement. / Owing to the development of the smart farming, some new studies need to be lead on a distributed instrumentation to measure soil moisture to control the irrigation.In the project IRRIS context, we realize a smart soil moisture sensor. First, we have to realize the sensing element of this sensor. We choose a capacitive detection to get a reactive sensor despite low cost. The body is a cylinder to be easily buried in the soil. The electrodes are made by electrochemical deposition on the plastic tube. Then, we design the measurement electronic. We compare two solutions, one with discrete components and the other software on embedded microcontroller. We submit those electronics at thermic variations to observe their comportment to create the law of compensation. Next we assemble the sensor according to two ways. The first, the multi sensor, forces the depths of sensing but reduces the costs by pooling the measurement electronic. The second, the mono sensor, frees the choice of depth but multiplies the number of sensors. We create at this step the sensor network thanks a wireless communication placed on 868MHz, an ISM band that we characterize in terms of range depending on the flow rate to optimize this communication. Finally, we observe the results of three measurement campaigns to validate the operating for different soil and cultures.This study ends in the realization of a sensor to measure soil moisture with a reduced cost relative to the industrial sensor on the market. Experiments prove its ease of use as well as its proper functioning.

Bakgrund: Lantbruket står inför stora framtida utmaningar som t.ex. stora befolkningsökningar och minskade jordbruksarealer. Ett förslag för att lösa en del av problemet och öka effektiviteten inom lantbruket är att implementera och använda olika digitala tjänster och produkter. Ett av koncepten för den digitala tekniken som har lyfts fram av bland annat EU är Smart farming. Konceptet är brett och innefattar många olika tekniska lösningar, varav en av dessa är kameraövervakning av boskapsdjur. Frågeställning: Har de lantbrukare som använder kameraövervakning av boskapsdjur upplevt en förändring av sin livskvalitet och har användningen av tekniken medfört några ekonomiska effekter? Metod: Ett kvalitativt angreppssätt valdes där sex lantbrukare intervjuades i semistrukturerade intervjuer. Resultat: De medverkande lantbrukarna var överlag positiva till kameraövervakningssystemen och flera av lantbrukarna anser att tekniken möjliggjort att de kunnat spara tid och att djur i viss utsträckning kunnat räddats. Flera av lantbrukarna menar också att användandet av kameraövervakningssystemen lett till positiva effekter gällande deras livskvalitet, där det framför allt var möjligheten att kunna spendera mer tid med familj och ökad flexibilitet som var bidragande. Slutsatser: Undersökningens resultat tyder på att kameraövervakningssystemen kan spara tid och pengar för lantbrukarna och att den upplevda livskvaliteten förbättras. Den grupp respondenter i undersökningen som upplevde störst effekter av kameraövervakningen var mindre lantbruk. Kameraövervakningen användes till flera olika ändamål, t.ex. brottsförebyggande, kalvning, personalsäkerhet, övervakning av foderbord, lösdrift samt gård och ägor.

Problem Statement: The world population is expected to rapidly increase, raising food security concerns across the world. This will impact Africa most severely. The use of innovative farming techniques and technology has proven to accelerate the production yields and improve resilience to vulnerabilities which impact agricultural productivity. The use of smart technologies in farming is mainly present among largescale commercial farms, with minimal representation in the smallholder farming sector. On the other hand, a substantial amount of food in developing countries is produced by small scale farmers. Research Objective: The purpose of the study is to investigate the usage of smart technologies by smallholder farmers in South Africa, and to establish how smart technology could support smallholder farmers in increasing productivity through a three-dimensional view that takes into consideration capital, labour, and land utilization. To this end, an interpretive research philosophy was adopted. Research Design: The study collected the data using semi-structured interviews. The sample for the study constituted of 10 smallholder farmers and 12 subject matter experts within the agriculture and technology domain. To strengthen rigour within the study, the interviews were supported by documents containing viewpoints about how technology is applied in the African context and how it may be introduced and ultimately applied in the South African context. The study employed a deductive approach to theory, applying the Sustainable Livelihoods Approach (SLA) as theoretical underpinning for the study. SLA consists of a pentagon of livelihood assets: physical, social, human, natural, and financial assets. The framework was extended to include technology as an asset due to its potential to contribute to improving the livelihoods of smallholder farmers. Findings: The study found minimal to no use of smart technologies by smallholder farmers in South Africa. The factors which limited the use of technology include PEST (Political, Environmental, Social and Technological) factors. To achieve successful usage of smart technologies, collaboration is required from government, the private sector, smallholder farmers, and communities. Research Contribution: The study aimed to expand on the limited literature on the use of smart farming in the context of smallholder farmers in a developing country context. In addition, it contributed to extending the pentagon of livelihoods to include smart technologies with respect to smallholder farmer livelihoods. Therefore, the findings of this study contributed to the broader body of knowledge. In addition, insights from this study may be gained by the Department of Agriculture, Forestry and Fisheries, smallholder farmers, agricultural entrepreneurs and technologists in formulate developmental strategies and policies to improve the productivity of smallholder farmers as well as their livelihoods as a strategy to increase their contribution to food security in Africa while alleviating household poverty.

[ES] Hay muchos trabajos relacionados con la automatización de procesos en agricultura. Con la revolución del Internet de las Cosas (del Inglés, Internet of things o IoT) están apareciendo en el mercado multitud de dispositivos capaces de interconectar sensores. Más enfocado a la agricultura intensiva, aparecen muchas comercializadoras de productos IoT que, aunque sus desarrolladores aseguran que son capaces de automatizar las tareas en los cultivos, vemos que no es así. Muchos productos tecnológicos desarrollados para ser usados en la agricultura de precisión, como son los programadores de riego tele-gestionados funcionan de forma independiente con otras tecnologías de la agricultura. En estos momentos y con el avance tecnológico actual, se debe integrar una programación de riego acorde a las necesidades reales del cultivo en tierra y con unas mediciones de necesidades de cultivo tomadas vía satélite o mediante dron desde el aire adaptando las variables de forma automática en una única plataforma de gestión. Si el patrón de producción de mi explotación funciona bien, la PLAtaforma TEcnológica Multimedia (PLATEM) permitirá compartir la estrategia seguida para que socios cooperativistas o personas que estén registrados en la red social, puedan verla y ver los contenidos publicados en ella sobre sistemas de control agrícolas. Esta tesis se centra en la investigación, diseño y desarrollo de nuevas tecnologías para integrar todos los sistemas presentes en un sistema automáticos, considerando, desde la monitorización de parámetros, hasta el procesado y toma de decisiones para una administración eficiente, siendo plata una herramienta óptima para la comunidad profesional de agricultores y con una usabilidad cercana al agricultor. Primeramente, se presentan trabajos previos relacionados con la captura de datos procedentes de cultivo y funcionamiento de riego a través del procesado de vídeo realizado con drones de vuelo autónomo. Seguidamente, se presentan los dispositivos presentes en la red inalámbrica de sensores orientada a captura de datos de los sensores terrestres y actuadores en sistemas de riego telegestionados de ultra bajo consumo energético. Por esto, nuestro trabajo se centra en redes de comunicaciones de banda estrecha, muy adecuadas para el uso en el medio rural. Nuestro sistema permite mantener un dispositivo comunicado y capaz de maniobrar las válvulas de hasta una extensión de 16 hectáreas con una pila comercial de 9 voltios toda una campaña de riego, sin necesidad de placas solares. Por último, toda la información e interoperabilidad de los apartados anteriores necesitan una gestión integral en un único sistema amigable con el usuario. En este punto presentamos un servidor con un motor de reglas de negocio y machine learning con autoaprendizaje capaz de generar decisiones para los controladores de riego, datos sensoriales de parcela o ambientales. Esta información es capaz de publicarse entre grupos sociales de usuarios e intercambiar métodos de trabajo y consignas. Todos los desarrollos y propuestas han sido precedidos de estudios de consumos energéticos en todos los dispositivos incluidos en el sistema. Además, se ha realizado un estudio en campo de las redes inalámbricas de sensores desplegadas en el medio rural bajo condiciones altamente problemáticas para comprobar el correcto funcionamiento del sistema entero. / [CA] Existeixen gran quantitat de treballs relacionats amb l'automatització de processos en agricultura. Amb la revolució la Internet de les coses (de l'anglès Internet of Things o IoT) estan apareixent al mercat multitud de dispositius capaços d'interconnectar sensors. Més enfocat a l'agricultura intensiva, s'estan comercialitzant productes IoT que, tot i que els seus desenvolupadors asseguren que són capaços d'automatitzar les tasques en els cultius, veiem que no és així. Molts productes tecnològics desenvolupats per a utilitzar-los a l'agricultura de precisió, com són els programadors de reg tele gestionats, funcionen de forma independent amb altres tecnologies usades en l'agricultura. En aquests moments i amb l'avanç tecnològic actual, existeix la possibilitat d'aplicar unes rutines de reg adequades amb les necessitats reals del cultiu en terra, combinat amb la mesura de les necessitats de cultiu preses via satèl·lit o mitjançant vehicles aeris no tripulats o dron des de l'aire, adaptant les variables de forma automàtica en una única plataforma de gestió. Si el patró de producció de la meva explotació funciona bé, la PLAtaforma TEcnològica Multimedia (PLATEM) permetrà compartir l'estratègia seguida per tal que socis cooperativistes o persones que estiguin registrats en la xarxa social, puguen vore-la i veure els continguts publicats en ella sobre sistemes de control agrícoles. Aquesta tesi es centra en la investigació, disseny i desenvolupament de noves tecnologies per a integrar tots els sistemes presents en un sistema automàtics, considerant, des de la monitorització de paràmetres, fins al processat i pressa de decisions per a una administració eficient, sent PLATEM una ferramenta òptima per a la comunitat professional d'agricultors i amb una usabilitat propera a l'agricultor. Primerament, es presenten treballs previs relacionats amb la captura de dades procedents de cultiu i funcionament de reg a través del processat de vídeo realitzat amb drons de vol autònom. Seguidament, es presenten els dispositius presents en la xarxa sense fils de sensors orientada a captura de dades terrestres i els actuadors utilitzats per al reg tele-gestionats d'ultra baix consum energètic. Per això, el nostre treball se centra en xarxes de comunicacions de banda estreta, molt adequades per a l'ús en el medi rural. El nostre sistema permet mantenir un dispositiu comunicat i capaç de controlar les vàlvules en terrenys extensió de 16 hectàrees amb una pila comercial de 9 volts durant tota una campanya de reg, sense necessitat de plaques solars. Finalment, tota la informació i interoperabilitat dels dispositius que integren la xarxa necessiten una gestió integral en un únic sistema amigable amb l'usuari. En aquest punt presentem un servidor amb un motor de regles de negoci que aplica machine learning amb autoaprenentatge capaç de generar decisions per als controladors de reg, tenint en compte les dades dels sensors de parcel·la i ambientals. Aquesta informació és capaç de publicar-se entre grups socials d'usuaris i intercanviar mètodes de treball i consignes. Tots els desenvolupaments i propostes han estat combinats amb estudis de consums energètics. A més, s'ha realitzat un estudi en camp de les xarxes sense fils de sensors desplegades en el medi rural sota condicions altament problemàtiques per a comprovar el correcte funcionament del sistema sencer. / [EN] There are many works related to the automation of processes in agriculture. With the revolution of the Internet of Things (IoT), many devices capable of interconnecting sensors are appearing on the market. The focus is on intensive agriculture in a market where designers and marketers of IoT products present designs for the automation of crop production, claiming systematic achievements that ar not always compatible with agricultural reality. Many technological products, such as remote or WiFi management of irrigation programmers, focused on precision agriculture, are independent systems with no connection to other agricultural technologies. At this time and with the current technological advance, it must be integrated irrigation schedules in response to the real time needs of crop nutrition determining cultivation needs are transmitted via satellite or drone, in a platform will automatically integrate intelligent irrigation systems on the plot of land in relation to thermal analysis and crop vigor. If the production patterns of a farm are promising, PLAtaforma TEcnologica Multimedia (PLATEM) will allow disseminate a strategy followed to cooperative partners or people who are registered in the social network can see it and see the contents published in it on agricultural control systems. This thesis will attempt to solve the above-mentioned issues: the integration from start to finish of data capture and open data decisions for a community of professional farmers. Firtsly, we will review the literature on data harvesting of irrigation decisions for cultivation through computer-processed videos recorded by drones with autonomous flight mapping. Next, the devices present in a Wireless Sensor Network (WSN) are presented aimed at capturing terrestrial sensory data connected to tele-managed irrigation systems with ultra-low energy consumption. Hence, the focus of this work is firmly set on narrowband communication networks that are very suitable for use in rural areas. Our system maintains a communicated device capable of maneuvering valves within an area of 16 hectares with a commercial 9-volt battery throughout an irrigation campaign, with no need for solar panels. Finally, all the information and interoperability described in the previous sections will need integral management. At this point, we present a server with a business rules engine and machine learning with (self-learning) decision trees capable of generating decisions for irrigation controllers. The basic layer consists of the data processing of data mining models. The second layer consists of model training with historical data and the third layer applies to machine learning that generates the best results for guidance on recommendations. This information can be published and shared on social media between groups of users for the exchange of working methods and opinions regarding crops, cultivation strategies and demonstration plots. All of the proposed developments and proposals have been grounded in systematic energy consumption studies of all devices in the intelligent irrigation systems. In addition, a field study is conducted of the WSN deployed in rural areas under highly problematic conditions to determine the correct functioning of the entire system. / Cambra Baseca, C. (2019). PLAtaforma TEcnológica Multimedia para la Agricultura de Precisión (PLATEM Precision Agriculture) [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/135820

Les réseaux de capteurs sans fil sont maintenant un moyen crédible de collecte de données sur les cultures. L'installation d'une structure de communication fixe pour relayer les données surveillées depuis la tête de grappe jusqu'à sa destination finale peut être soit impraticable en raison de la topologie du terrain, soit prohibitive en raison du coût initial élevé. Une solution plausible consiste à utiliser des véhicules aériens sans pilote (UAV) comme moyen alternatif de collecte de données et de contrôle de supervision limité de l'état des détecteurs. Dans cet article, nous considérons le cas des parcelles agricoles disjointes comprenant chacune des grappes de capteurs, organisées de manière prédéterminée en fonction des objectifs d'élevage. Cette recherche vise à trouver une solution optimale pour la recherche de UAV et la collecte de données à partir de tous les capteurs installés dans un champ de culture. En outre, le protocole de routage des capteurs tiendra compte d'un compromis entre la gestion de l'énergie et les frais généraux de diffusion des données. Le système proposé est évalué en utilisant un modèle simulé et il devrait trouver une classe parmi toutes les sous-considérations. / Wireless sensor networks are now a credible means for crop data collection. The installation of a fixed communication structure to relay the monitored data from the cluster head to its final destination can either be impractical because of land topology or prohibitive due to high initial cost. A plausible solution is to use Unmanned Aerial Vehicles (UAV) as an alternative means for both data collection and limited supervisory control of sensors status. In this paper, we consider the case of disjoint farming parcels each including clusters of sensors, organized in a predetermined way according to farming objectives. This research focuses to drive an optimal solution for UAV search and data gathering from all sensors installed in a crop field. Furthermore, the sensor routing protocol will take into account a tradeoff between energy management and data dissemination overhead.The proposed system is evaluated by using a simulated model and it should find out a class among all under consideration.

Artificial Intelligence (AI) is increasingly used in different parts of society for providing decision support in various activities. The agricultural sector is anticipated to benefit from an increased usage of AI and smart devices, a concept called smart farming technologies. Since the agricultural sector faces several simultaneous challenges, such as shrinking marginals, complicated pan-European regulations, and demands to mitigate the environmental footprint, there are great expectations that smart farming will benefit both individual farmers and industry stakeholders. However, most previous research focuses only on a small set of characteristics for implementing and optimising specific smart farming technologies, without considering all possible aspects and effects. This thesis investigates both technical and non-technical opportunities and hurdles when implementing AI in Swedish agricultural businesses. Three sectors in agriculture are scrutinized: arable farming, milk production and beef production. As a foundation for the thesis, a literature review revises former research on smart farming. Thereafter, an interview study with 27 respondents both explores the susceptibility and maturity of smart farming technologies and provides examples of technical requirements of three chosen applications of AI in agriculture. Findings of the study include a diverse set of aspects that both enable and obstruct the transition. Main identified opportunities are the importance smart farming has on the strategic agendas of several industry stakeholders, the general trend towards software technology as a service through shared machinery, the vast amount of existing data, and the large interest from farmers towards new technology. Contrasting, the thesis identifies main hurdles as technical and legislative challenges to data ownership, potential cybersecurity threats, the need for a well-articulated business case, and the sometimes lacking technical knowledge within the sector. The thesis concludes that the macro trend points towards a smart farming transition but that the speed of the transformation will depend on the resolutions for the identified obstacles.

Die kontinuierliche Überwachung von Pflanzenparametern spielt eine wichtige Rolle in der Präzisionslandwirtschaft. Als in situ Monitoring-Systeme erscheinen drahtlose Sensornetzwerke (engl. Wireless Sensor Networks (WSNs)) geeignet, um den Zustand von Kulturpflanzen zu erfassen und diesen in stets aktuelle Parameterkarten zu transformieren. Derartige Karten können potenzielle wachstums- und ertragsmindernde Faktoren frühzeitig identifizieren und Entscheidungshilfen geben, die zu einer ortsdifferenzierten, zielgerichteten und nachhaltigen Bewirtschaftung landwirtschaftlicher Produktionsflächen beitragen. Die vorliegende kumulative Dissertation beschäftigt sich in diesem Zusammenhang mit der automatisierten und kosteneffizienten in situ Erfassung eines wichtigen Pflanzenparameters, dem sogenannten Blattflächenindex (engl. Leaf Area Index (LAI)). Mittels handelsüblicher WSN-Hardware wird zunächst ein kostengünstiger Sensor-Prototyp für eine passive, transmissionsbasierte LAI-Erfassung konzipiert und, begleitet durch Feldkampagnen, experimentell weiterentwickelt. Im Verlauf der Arbeit wird eine auf die spezielle Anwendung zugeschnittene Netzwerkarchitektur entworfen, die den Prototypen in ein ganzheitliches Langzeit-Monitoring-System überführt. Durch exemplarisch realisierte Deployments an zwei unterschiedlichen Standorten und den daraus erfassten empirischen Datensätzen wird das Potenzial drahtloser Sensornetzwerke für eine kontinuierliche und zeitlich hochauflösende LAI-Erfassung analysiert. Dabei werden effektive Methoden zur Prozessierung und Filterung von in situ Sensordaten entwickelt und untersucht, inwieweit diese die Qualität der abgeleiteten LAI-Schätzung verbessern. Ein Schwerpunkt der empirischen Potenzialanalyse liegt dabei auf der differenzierten Erfassung von sortenspezifischen und trockenstressbedingten Veränderungen. Weiterhin wird der Einfluss von Umwelt und Vegetation auf die Qualität drahtloser Verbindungen in landwirtschaftlichen WSN-Deployments betrachtet. Basierend auf dem empirischen Datensatz wird gezeigt, dass das Pflanzenwachstum die Qualität exemplarischer Verbindungen beeinträchtigt. Aus dieser Beobachtung wird ein Modell für ein signalstärkebasiertes Pflanzen-Monitoring abgeleitet und die generelle Machbarkeit dieses neuartigen Ansatzes untersucht.