Remote sensing data acquired from satellites are a vital information source for precision agricul... more Remote sensing data acquired from satellites are a vital information source for precision agriculture to assess current crop conditions. Field measurements of plant parameters, like the leaf area index (LAI), serve as a crucial basis to validate parameter maps derived from satellite images. Traditionally, in-situ LAI measurements are collected manually. Therefore, the assessment is cost-intensive and the temporal availability of measurements is limited. Measurements provided by small sensor devices organized in a wireless sensor network (WSN) are a low-cost alternative to manual field measurements. They allow a precise LAI determination with high temporal resolution at many different locations in a field or even an entire region. These information are highly demanded for the validation of spatial information on crop conditions derived from image data acquired by modern satellites like Sentinel-2.
In recent decades, due to the increasing weight of agricultural machineries, undesirable soil com... more In recent decades, due to the increasing weight of agricultural machineries, undesirable soil compaction has become a severe factor for soil degradation. It does not only have negative ecological, but also economic effects. Successfully detecting, monitoring and predicting depths of ruts that were used by heavy vehicles can potentially reduce soil compaction. A crucial task is to generate real-world data at site-specific locations. UAV-based approaches have the advantage of providing sufficient spatial coverage and resolution to assess vital information, which can be used to directly evaluate the compaction resulting from the utilization of these heavy machineries. This information could be used for agricultural predictions, optimized routing and best time for treatments, soil regeneration purposes and many more. Therefore, the aim of this research was to spatially detect the depth of ruts, caused by heavy farm machineries on agricultural fields with consumer-grade Unmanned Aerial Vehicles (UAVs).We therefore created a semi-automatic processing pipeline for UAV based data. The georeferenced RGB orthomosaic was used to spatially predict lanes, in the early stages of the crop cycle, by employing a Machine Learning approach. This prediction was subsequently used to extract the height information of the rut and the surrounding area from the SfM (Structure from Motion) Digital Elevation Model. As a reference method for the absolute height information, we compared this DEM (DJI Phantom 4) to the UAV - LiDAR derived DEM (RIEGL miniVUX-1UAV). For both systems, no substantial difference in the quality of the evaluated compaction depth was observed. This allows the use of low-cost UAV RGB systems to contribute to the ongoing research on soil compaction.
Semi-natural grasslands (SNGs) are an essential part of European cultural landscapes. They are an... more Semi-natural grasslands (SNGs) are an essential part of European cultural landscapes. They are an important habitat for many animal and plant species and offer a variety of ecological functions. Diverse plant communities have evolved over time depending on environmental and management factors in grasslands. These different plant communities offer multiple ecosystem services and also have an effect on the forage value of fodder for domestic livestock. However, with increasing intensification in agriculture and the loss of SNGs, the biodiversity of grasslands continues to decline. In this paper, we present a method to spatially classify plant communities in grasslands in order to identify and map plant communities and weed species that occur in a semi-natural meadow. For this, high-resolution multispectral remote sensing data were captured by an unmanned aerial vehicle (UAV) in regular intervals and classified by a convolutional neural network (CNN). As the study area, a heterogeneous...
Klee-Gras-Bestände haben eine große Bedeutung als Futterpflanzen sowie als Stickstoffquelle. Die ... more Klee-Gras-Bestände haben eine große Bedeutung als Futterpflanzen sowie als Stickstoffquelle. Die Bestandszusammensetzung aus Klee und Gras verändert sich je nach Bodenbedingung (Stickstoffversorgung, Wasserhaltekapazität, Boden-pH etc.) und Bewirtschaftungsform mit der Zeit. UAV-gestützte Bilddaten sind eine effektive Möglichkeit, um Heterogenität im Pflanzenbestand zu erkennen. Diese können die Grundlage für ein teilflächenspezifisches Management bilden. Zu diesem Zweck wurden auf einer ökologisch bewirtschafteten Kleegrasfläche in Belm bei Osnabrück, die sich in eine gedüngte und ungedüngte Teilfläche aufteilt, zu mehreren Terminen im Frühjahr und Sommer drohnengestützte RGBund Multispektralbilder aufgenommen. Räumliche und temporale Heterogenitäten, welche vermutlich auf Bodenunterschiede zurückzuführen sind, konnten mithilfe von Vegetationsindizes aus den Bilddaten des Kleegrasbestandes ermitteln werden. Aufgrund der Trockenheit im Frühsommer 2020 wurde im Laufe des Untersuchung...
Leaf area index (LAI) and above ground biomass dry matter (DM) are key variables for crop growth ... more Leaf area index (LAI) and above ground biomass dry matter (DM) are key variables for crop growth monitoring and yield estimation. High prediction accuracies of these parameters are a vital prerequisite for sophisticated yield projections. The aim of the study was to examine the predictive ability of partial least squares regression (PLSR) for LAI and DM retrieval from hyperspectral (EnMAP), superspectral (Sentinel-2), and multispectral (Landsat 8, RapidEye) remote sensing data based on field reflectance measurements. Data was acquired from several crop types (wheat, rye, barley, rape, potato, sugar beet) during field campaigns in three different regions of Germany between the years 2011 and 2014. The field reflectance measurements were resampled to match the different spectral resolutions. Continuous reflectance and resampled data were transformed using five spec-tral pre-processing techniques. Continuous data were used for comparison and served as best case scenario. The predictive...
The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th... more The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th, 2011, June 27th, 2011 and May 24th, 2012 consisting of 367 and 368 spectral bands, respective-ly, ranging from VIS to SWIR (400 - 2500 nm) wavelength regions. The hyperspectral image data was acquired in the framework of the EnMAP preparation project HyLand (Hyperspectral remote sensing for the assessment of crop and soil parameters in precision farming and yield estimation). Within the project, innovative techniques were developed to derive crop and soil parameters from hyper-spectral remote sensing and terrestrial laser scanning data, which served as input parameters for novel yield estimation models.
With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of de... more With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of deep learning, new opportunities have emerged in remote sensing to assess biophysical plant parameters. In this study, we investigated the potential of UAV-borne RGB data and convolutional neural networks (CNNs) to estimate the leaf area index (LAI) of winter wheat during two cropping seasons. In this context, spectral RGB and geometric plant information based on a normalized surface model (nDSM) were used as input variables. The results of the study demonstrated the suitability of optical UAV data and CNNs for LAI estimation of winter wheat at different growth stages and under various lightning conditions. The combination of RGB data and plant structures provided the best overall prediction accuracy (<inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.83$ </tex-math></inline-formula>) compared to the models with only one input source (RGB: <inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.58$ </tex-math></inline-formula>, nDSM: <inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.75$ </tex-math></inline-formula>). Especially the estimation of low and high LAI values was improved using the complementary image information. Moreover, the results showed that the CNN models outperformed two classical machine learning (ML) approaches in terms of accuracy.
In order to locate historical traces, drone-based Laserscanning has become increasingly popular i... more In order to locate historical traces, drone-based Laserscanning has become increasingly popular in archaeological prospection and historical conflict landscapes research. The low resolution of aircraft-based Laserscanning is not suitable for small-scale detailed analysis so that high-resolution UAV-based LiDAR data are required. However, many of the existing studies lack a systematic approach to UAV-LiDAR data acquisition and point cloud filtering. We use this methodology to detect anthropogenic terrain anomalies. In this study, we systematically investigated different influencing factors on UAV-LiDAR data acquisition. The flight parameters speed and altitude above ground were systematically varied. In addition, different vegetation cover and seasonal acquisition times were compared, and we evaluated three different types of filter algorithms to separate ground from non-ground. It could be seen from our experiments that for the detection of subsurface anomalies in treeless open terr...
The exploration and monitoring of bio-physical crop parameters enabled by modern sensor technolog... more The exploration and monitoring of bio-physical crop parameters enabled by modern sensor technology in the context of smart farming is crucial for a sustainable agriculture. The leaf area index (LAI) is one of the most important parameters which serves as an indicator for the vital condition of plants. This proposal presents Smart fLAIr, a smartphone application developed for a reliable in-situ LAI estimation. It leverages a non-destructive, radiation-based approach using the smartphone’s Ambient Light Sensor (ALS) and offers a cost-efficient alternative to commercial plant canopy analyzers. Without special hardand software requirements and due to a focus on simplicity and ease of use, a wide scientific user group, that is interested in a feasible LAI acquisition, is reached by the application.
Remote sensing data acquired from satellites are a vital information source for precision agricul... more Remote sensing data acquired from satellites are a vital information source for precision agriculture to assess current crop conditions. Field measurements of plant parameters, like the leaf area index (LAI), serve as a crucial basis to validate parameter maps derived from satellite images. Traditionally, in-situ LAI measurements are collected manually. Therefore, the assessment is cost-intensive and the temporal availability of measurements is limited. Measurements provided by small sensor devices organized in a wireless sensor network (WSN) are a low-cost alternative to manual field measurements. They allow a precise LAI determination with high temporal resolution at many different locations in a field or even an entire region. These information are highly demanded for the validation of spatial information on crop conditions derived from image data acquired by modern satellites like Sentinel-2.
In recent decades, due to the increasing weight of agricultural machineries, undesirable soil com... more In recent decades, due to the increasing weight of agricultural machineries, undesirable soil compaction has become a severe factor for soil degradation. It does not only have negative ecological, but also economic effects. Successfully detecting, monitoring and predicting depths of ruts that were used by heavy vehicles can potentially reduce soil compaction. A crucial task is to generate real-world data at site-specific locations. UAV-based approaches have the advantage of providing sufficient spatial coverage and resolution to assess vital information, which can be used to directly evaluate the compaction resulting from the utilization of these heavy machineries. This information could be used for agricultural predictions, optimized routing and best time for treatments, soil regeneration purposes and many more. Therefore, the aim of this research was to spatially detect the depth of ruts, caused by heavy farm machineries on agricultural fields with consumer-grade Unmanned Aerial Vehicles (UAVs).We therefore created a semi-automatic processing pipeline for UAV based data. The georeferenced RGB orthomosaic was used to spatially predict lanes, in the early stages of the crop cycle, by employing a Machine Learning approach. This prediction was subsequently used to extract the height information of the rut and the surrounding area from the SfM (Structure from Motion) Digital Elevation Model. As a reference method for the absolute height information, we compared this DEM (DJI Phantom 4) to the UAV - LiDAR derived DEM (RIEGL miniVUX-1UAV). For both systems, no substantial difference in the quality of the evaluated compaction depth was observed. This allows the use of low-cost UAV RGB systems to contribute to the ongoing research on soil compaction.
Semi-natural grasslands (SNGs) are an essential part of European cultural landscapes. They are an... more Semi-natural grasslands (SNGs) are an essential part of European cultural landscapes. They are an important habitat for many animal and plant species and offer a variety of ecological functions. Diverse plant communities have evolved over time depending on environmental and management factors in grasslands. These different plant communities offer multiple ecosystem services and also have an effect on the forage value of fodder for domestic livestock. However, with increasing intensification in agriculture and the loss of SNGs, the biodiversity of grasslands continues to decline. In this paper, we present a method to spatially classify plant communities in grasslands in order to identify and map plant communities and weed species that occur in a semi-natural meadow. For this, high-resolution multispectral remote sensing data were captured by an unmanned aerial vehicle (UAV) in regular intervals and classified by a convolutional neural network (CNN). As the study area, a heterogeneous...
Klee-Gras-Bestände haben eine große Bedeutung als Futterpflanzen sowie als Stickstoffquelle. Die ... more Klee-Gras-Bestände haben eine große Bedeutung als Futterpflanzen sowie als Stickstoffquelle. Die Bestandszusammensetzung aus Klee und Gras verändert sich je nach Bodenbedingung (Stickstoffversorgung, Wasserhaltekapazität, Boden-pH etc.) und Bewirtschaftungsform mit der Zeit. UAV-gestützte Bilddaten sind eine effektive Möglichkeit, um Heterogenität im Pflanzenbestand zu erkennen. Diese können die Grundlage für ein teilflächenspezifisches Management bilden. Zu diesem Zweck wurden auf einer ökologisch bewirtschafteten Kleegrasfläche in Belm bei Osnabrück, die sich in eine gedüngte und ungedüngte Teilfläche aufteilt, zu mehreren Terminen im Frühjahr und Sommer drohnengestützte RGBund Multispektralbilder aufgenommen. Räumliche und temporale Heterogenitäten, welche vermutlich auf Bodenunterschiede zurückzuführen sind, konnten mithilfe von Vegetationsindizes aus den Bilddaten des Kleegrasbestandes ermitteln werden. Aufgrund der Trockenheit im Frühsommer 2020 wurde im Laufe des Untersuchung...
Leaf area index (LAI) and above ground biomass dry matter (DM) are key variables for crop growth ... more Leaf area index (LAI) and above ground biomass dry matter (DM) are key variables for crop growth monitoring and yield estimation. High prediction accuracies of these parameters are a vital prerequisite for sophisticated yield projections. The aim of the study was to examine the predictive ability of partial least squares regression (PLSR) for LAI and DM retrieval from hyperspectral (EnMAP), superspectral (Sentinel-2), and multispectral (Landsat 8, RapidEye) remote sensing data based on field reflectance measurements. Data was acquired from several crop types (wheat, rye, barley, rape, potato, sugar beet) during field campaigns in three different regions of Germany between the years 2011 and 2014. The field reflectance measurements were resampled to match the different spectral resolutions. Continuous reflectance and resampled data were transformed using five spec-tral pre-processing techniques. Continuous data were used for comparison and served as best case scenario. The predictive...
The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th... more The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th, 2011, June 27th, 2011 and May 24th, 2012 consisting of 367 and 368 spectral bands, respective-ly, ranging from VIS to SWIR (400 - 2500 nm) wavelength regions. The hyperspectral image data was acquired in the framework of the EnMAP preparation project HyLand (Hyperspectral remote sensing for the assessment of crop and soil parameters in precision farming and yield estimation). Within the project, innovative techniques were developed to derive crop and soil parameters from hyper-spectral remote sensing and terrestrial laser scanning data, which served as input parameters for novel yield estimation models.
With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of de... more With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of deep learning, new opportunities have emerged in remote sensing to assess biophysical plant parameters. In this study, we investigated the potential of UAV-borne RGB data and convolutional neural networks (CNNs) to estimate the leaf area index (LAI) of winter wheat during two cropping seasons. In this context, spectral RGB and geometric plant information based on a normalized surface model (nDSM) were used as input variables. The results of the study demonstrated the suitability of optical UAV data and CNNs for LAI estimation of winter wheat at different growth stages and under various lightning conditions. The combination of RGB data and plant structures provided the best overall prediction accuracy (<inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.83$ </tex-math></inline-formula>) compared to the models with only one input source (RGB: <inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.58$ </tex-math></inline-formula>, nDSM: <inline-formula> <tex-math notation="LaTeX">$r^{2} = 0.75$ </tex-math></inline-formula>). Especially the estimation of low and high LAI values was improved using the complementary image information. Moreover, the results showed that the CNN models outperformed two classical machine learning (ML) approaches in terms of accuracy.
In order to locate historical traces, drone-based Laserscanning has become increasingly popular i... more In order to locate historical traces, drone-based Laserscanning has become increasingly popular in archaeological prospection and historical conflict landscapes research. The low resolution of aircraft-based Laserscanning is not suitable for small-scale detailed analysis so that high-resolution UAV-based LiDAR data are required. However, many of the existing studies lack a systematic approach to UAV-LiDAR data acquisition and point cloud filtering. We use this methodology to detect anthropogenic terrain anomalies. In this study, we systematically investigated different influencing factors on UAV-LiDAR data acquisition. The flight parameters speed and altitude above ground were systematically varied. In addition, different vegetation cover and seasonal acquisition times were compared, and we evaluated three different types of filter algorithms to separate ground from non-ground. It could be seen from our experiments that for the detection of subsurface anomalies in treeless open terr...
The exploration and monitoring of bio-physical crop parameters enabled by modern sensor technolog... more The exploration and monitoring of bio-physical crop parameters enabled by modern sensor technology in the context of smart farming is crucial for a sustainable agriculture. The leaf area index (LAI) is one of the most important parameters which serves as an indicator for the vital condition of plants. This proposal presents Smart fLAIr, a smartphone application developed for a reliable in-situ LAI estimation. It leverages a non-destructive, radiation-based approach using the smartphone’s Ambient Light Sensor (ALS) and offers a cost-efficient alternative to commercial plant canopy analyzers. Without special hardand software requirements and due to a focus on simplicity and ease of use, a wide scientific user group, that is interested in a feasible LAI acquisition, is reached by the application.
Uploads
Papers