The knowledge about heterogeneity on agricultural fields is essential for a sustainable and effective field management. This study investigates the performance of Synthetic Aperture Radar (SAR) data of the Sentinel-1 satellites to detect variability between and within agricultural fields in two test sites in Germany. For this purpose, the temporal profiles of the SAR backscatter in VH and VV polarization as well as their ratio VH/VV of multiple wheat and barley fields are illustrated and interpreted considering differences between acquisition settings, years, crop types and fields. Within-field variability is examined by comparing the SAR backscatter with several crop parameters measured at multiple points in 2017 and 2018. Structural changes, particularly before and after heading, as well as moisture and crop cover differences are expressed in the backscatter development. Furthermore, the crop parameters wet and dry biomass, absolute and relative vegetation water content, leaf area index (LAI) and plant height are related to SAR backscatter parameters using linear and exponential as well as multiple regression. The regression performance is evaluated using the coefficient of determination (R ) and the root mean square error (RMSE) and is strongly dependent on the phenological growth stage. Wheat shows R values around 0.7 for VV backscatter and multiple regression and most crop parameters before heading. Single fields even reach R values above 0.9 for VV backscatter and for multiple regression related to plant height with RMSE values around 10 cm. The formulation of clear rules remains challenging, as there are multiple influencing factors and uncertainties and a lack of conformity.
Soil degradation is a major threat for European soils and therefore, the European Commission recommends intensifying research on soil monitoring to capture changes over time and space. Imaging spectroscopy is a promising technique to create spatially accurate topsoil maps based on hyperspectral remote sensing data. We tested the application of a local partial least squares regression (PLSR) to airborne HySpex and simulated satellite EnMAP (Environmental Mapping and Analysis Program) data acquired in north-eastern Germany to quantify the soil organic carbon (SOC) content. The approach consists of two steps: (i) the local PLSR uses the European LUCAS (land use/cover area frame statistical survey) Soil database to quantify the SOC content for soil samples from the study site in order to avoid the need for wet chemistry analyses, and subsequently (ii) a remote sensing model is calibrated based on the local PLSR SOC results and the corresponding image spectra. This two-step approach is compared to a traditional PLSR approach using measured SOC contents from local samples. The prediction accuracy is high for the laboratory model in the first step with R2 = 0.86 and RPD = 2.77. The HySpex airborne prediction accuracy of the traditional approach is high and slightly superior to the two-step approach (traditional: R2 = 0.78, RPD = 2.19; two-step: R2 = 0.67, RPD = 1.79). Applying the two-step approach to simulated EnMAP imagery leads to a lower but still reasonable prediction accuracy (traditional: R2 = 0.77, RPD = 2.15; two-step: R2 = 0.48, RPD = 1.41). The two-step models of both sensors were applied to all bare soils of the respective images to produce SOC maps. This local PLSR approach, based on large scale soil spectral libraries, demonstrates an alternative to SOC measurements from wet chemistry of local soil samples. It could allow for repeated inexpensive SOC mapping based on satellite remote sensing data as long as spectral measurements of a few local samples are available for model calibration.
The machine learning method, random forest (RF), is applied in order to derive biophysical and structural vegetation parameters from hyperspectral signatures. Hyperspectral data are, among other things, characterized by their high dimensionality and autocorrelation. Common multivariate regression approaches, which usually include only a limited number of spectral indices as predictors, do not make full use of the available information. In contrast, machine learning methods, such as RF, are supposed to be better suited to extract information on vegetation status. First, vegetation parameters are extracted from hyperspectral signatures simulated with the radiative transfer model, PROSAIL. Second, the transferability of these results with respect to laboratory and field measurements is investigated. In situ observations of plant physiological parameters and corresponding spectra are gathered in the laboratory for summer barley (Hordeum vulgare). Field in situ measurements focus on winter crops over several growing seasons. Chlorophyll content, Leaf Area Index and phenological growth stages are derived from simulated and measured spectra. RF performs very robustly and with a very high accuracy on PROSAIL simulated data. Furthermore, it is almost unaffected by introduced noise and bias in the data. When applied to laboratory data, the prediction accuracy is still good (C\(_{ab}\): \(R^2\) = 0.94/ LAI: \(R^2\) = 0.80/BBCH (Growth stages of mono-and dicotyledonous plants) : \(R^2\) = 0.91), but not as high as for simulated spectra. Transferability to field measurements is given with prediction levels as high as for laboratory data (C\(_{ab}\): \(R^2\) = 0.89/LAI: \(R^2\) = 0.89/BBCH: \(R^2\) = \(\sim\)0.8). Wavelengths for deriving plant physiological status based on simulated and measured hyperspectral signatures are mostly selected from appropriate spectral regions (both field and laboratory): 700–800 nm regressing on C\(_{ab}\) and 800–1300 nm regressing on LAI. Results suggest that the prediction accuracy of vegetation parameters using RF is not hampered by the high dimensionality of hyperspectral signatures (given preceding feature reduction). Wavelengths selected as important for prediction might, however, vary between underlying datasets. The introduction of changing environmental factors (soil, illumination conditions) has some detrimental effect, but more important factors seem to stem from measurement uncertainties and plant geometries.
In the face of rapid global change it is imperative to preserve geodiversity for the overall conservation of biodiversity. Geodiversity is important for understanding complex biogeochemical and physical processes and is directly and indirectly linked to biodiversity on all scales of ecosystem organization. Despite the great importance of geodiversity, there is a lack of suitable monitoring methods. Compared to conventional in-situ techniques, remote sensing (RS) techniques provide a pathway towards cost-effective, increasingly more available, comprehensive, and repeatable, as well as standardized monitoring of continuous geodiversity on the local to global scale. This paper gives an overview of the state-of-the-art approaches for monitoring soil characteristics and soil moisture with unmanned aerial vehicles (UAV) and air- and spaceborne remote sensing techniques. Initially, the definitions for geodiversity along with its five essential characteristics are provided, with an explanation for the latter. Then, the approaches of spectral traits (ST) and spectral trait variations (STV) to record geodiversity using RS are defined. LiDAR (light detection and ranging), thermal and microwave sensors, multispectral, and hyperspectral RS technologies to monitor soil characteristics and soil moisture are also presented. Furthermore, the paper discusses current and future satellite-borne sensors and missions as well as existing data products. Due to the prospects and limitations of the characteristics of different RS sensors, only specific geotraits and geodiversity characteristics can be recorded. The paper provides an overview of those geotraits.
The time series of synthetic aperture radar (SAR) data are commonly and successfully used to monitor the biophysical parameters of agricultural fields. Because, until now, mainly backscatter coefficients have been analysed, this study examines the potentials of entropy, anisotropy, and alpha angle derived from a dual-polarimetric decomposition of Sentinel-1 data to monitor crop development. The temporal profiles of these parameters are analysed for wheat and barley in the vegetation periods 2017 and 2018 for 13 fields in two test sites in Northeast Germany. The relation between polarimetric parameters and biophysical parameters observed in the field is investigated using linear and exponential regression models that are evaluated using the coefficient of determination (R2) and the root mean square error (RMSE). The performance of single regression models is furthermore compared to those of multiple regression models, including backscatter coefficients in VV and VH polarisation as well as polarimetric decomposition parameters entropy and alpha. Characteristic temporal profiles of entropy, anisotropy, and alpha reflecting the main phenological changes in plants as well as the meteorological differences between the two years are observed for both crop types. The regression models perform best for data from the phenological growth stages tillering to booting. The highest R2 values of the single regression models are reached for the plant height of wheat related to entropy and anisotropy with R2 values of 0.64 and 0.61, respectively. The multiple regression models of VH, VV, entropy, and alpha outperform single regression models in most cases. R2 values of multiple regression models of plant height (0.76), wet biomass (0.7), dry biomass (0.7), and vegetation water content (0.69) improve those of single regression models slightly by up to 0.05. Additionally, the RMSE values of the multiple regression models are around 10% lower compared to those of single regression models. The results indicate the capability of dual-polarimetric decomposition parameters in serving as meaningful input parameters for multiple regression models to improve the prediction of biophysical parameters. Additionally, their temporal profiles indicate phenological development dependent on meteorological conditions. Knowledge about biophysical parameter development and phenology is important for farmers to monitor crop growth variability during the vegetation period to adapt and to optimize field management.
In this article, we propose a deep learning-based algorithm for the classification of crop types from Sentinel-1 and Sentinel-2 time series data which is based on the celebrated transformer architecture. Crucially, we enable our algorithm to do early classification, i.e., predict crop types at arbitrary time points early in the year with a single trained model (progressive intra-season classification). Such early season predictions are of practical relevance for instance for yield forecasts or the modeling of agricultural water balances, therefore being important for the public as well as the private sector. Furthermore, we improve the mechanism of combining different data sources for the prediction task, allowing for both optical and radar data as inputs (multi-modal data fusion) without the need for temporal interpolation. We can demonstrate the effectiveness of our approach on an extensive data set from three federal states of Germany reaching an average F1 score of using data of a complete growing season to predict the eight most important crop types and an F1 score above when doing early classification at least one month before harvest time. In carefully chosen experiments, we can show that our model generalizes well in time and space.