Figure 5 - uploaded by Dimitri Goffart
Content may be subject to copyright.
Based on 10 fold cross-validation RMSE, top 5 of the models tested (highlighted bars) for the 2017 whole dataset (full), for mixed cover, for mustard and for phacelia. The italic black number is the R 2 of the model.
Source publication
Winter cover crops, used as green manure, can supply up to 45 units of nitrogen per hectare to the following summer crops. In order to contribute to the establishment of the nitrogen balance sheet for fertilisation recommendation of subsequent main crop at field scale, this supply is currently derived from the biomass production, classically estima...
Contexts in source publication
Context 1
... total, more than 450 models were tested (6 model types x 76 VIs/BVs). The selection of the five best models per winter cover crop category, based on the 10-fold CVRMSE, is presented in figure 5. Best models usually consider an exponential (y = ae bx ) or a power (y = ax b ) relationship (figures 5 and 6). ...
Context 2
... this last category, a simple linear regression could be used instead of the exponential model. Within each category, the top five ( figure 5) highlights two (for full) to five (for mixed) VIs that are strongly correlated. Except for the NDReSw, all indices use the B8 or B8A bands (NIR) in combination with one or two other bands. ...
Citations
... Jennewein et al. [42] assessed the use of Sentinel-2 and Sentinel-1 (SAR) imagery to estimate winter cover crop biomass across 27 fields in Maryland over multiple seasons and highlighted the significance of red-edge bands in addressing saturation issues in biomass estimation, and also some limitations related to species-level effects. Goffart et al. [43] assessed the suitability of Sentinel-2 satellite data for estimating the biomass production of winter cover crops in Belgium, including various single and mixed cover crop species. In their study, they established empirical relationships between biomass and 73 vegetation indices (VIs) derived from multiple bands, and compared the satellite-based biomass estimation with visual farmer-based estimates and reference field measurements. ...
... This approach aims to assess a multitude of potential band combinations offered by Sentinel-2. Notably, in line with recommendations by Jaramaz et al. [55] and Delegido et al. [56], the incorporation of the red-edge bands is anticipated to augment the accuracy of estimating crop biophysical parameters, such as Leaf Area Index (LAI), which has a direct correlation with aerial biomass [43]. The adopted methodology for cloud and shadow masking involved a combination of the sentinel2cloudless algorithm with the Cloud Displacement Index (CDI). ...
... To achieve the main objective of this study, which is devising a robust methodology to estimate winter fallow cover crop biomass in France using Sentinel-2 data, our initial step involved an analysis to determine the most effective combinations of spectral bands, vegetation indices (VIs), and statistical models. Employing a cross-validation approach akin to methodologies previously utilized by Goffart et al. [43] and Swoish et al. [62], we used the last image before in situ sampling. ...
Cover crops play a pivotal role in mitigating climate change by bolstering carbon sequestration through biomass production and soil integration. However, current methods for quantifying cover crop biomass lack spatial precision and objectivity. Thus, our research aimed to devise a remote-sensing-based approach to estimate cover crop biomass across various species and mixtures during fallow periods in France. Leveraging Sentinel-2 optical data and machine learning algorithms, we modeled biomass across 50 fields representative of France’s diverse cropping practices and climate types. Initial tests using traditional empirical relationships between vegetation indices/spectral bands and dry biomass revealed challenges in accurately estimating biomass for mixed cover crop categories due to spectral interference from grasses and weeds, underscoring the complexity of modeling diverse agricultural conditions. To address this challenge, we compared several machine learning algorithms (Support Vector Machine, Random Forest, and eXtreme Gradient Boosting) using spectral bands and vegetation indices from the latest available image before sampling as input. Additionally, we developed an approach that incorporates dense optical time series of Sentinel-2 data, generated using a Radial Basis Function for interpolation. Our findings demonstrated that a Random Forest model trained with dense time series data during the cover crop development period yielded promising results, with an average R-squared (r2) value of 0.75 and root mean square error (RMSE) of 0.73 t·ha−1, surpassing results obtained from methods using single-image snapshots (r2 of 0.55). Moreover, our approach exhibited robustness in accounting for factors such as crop species diversity, varied climatic conditions, and the presence of weed vegetation—essential for approximating real-world conditions. Importantly, its applicability extends beyond France, holding potential for global scalability. The availability of data for model calibration across diverse regions and timeframes could facilitate broader application.
... For example, previous studies have used multi-spectral optical imagery, such as Landsat, and Sentinel-2, to map the presence of cover crops by detecting vegetation greenness outside of the primary growing season Seifert et al., 2019;Fan et al., 2020;Thieme et al., 2020). These studies have also found that vegetation indices can be used to map the phenology, sowing time, and termination date of cover crops (Fan et al., 2020;Gao et al., 2020) as well as their performance by estimating biomass Breunig et al., 2020;Thieme et al., 2020;Goffart et al., 2021) and biomass nitrogen content (Xia et al., 2021). Recent work has also shown that radar and thermal data can be used in combination with optical imagery to improve cover crop area and biomass estimation (Barnes et al., 2021;Jennewein et al., 2022). ...
... Recent work has also shown that radar and thermal data can be used in combination with optical imagery to improve cover crop area and biomass estimation (Barnes et al., 2021;Jennewein et al., 2022). These methods have been applied to map cover crops in multiple farming systems, including in the eastern United States , the United States Midwest (Seifert et al., 2019;KC et al., 2021), the Netherlands (Fan et al., 2020), Belgium (Goffart et al., 2021), and Brazil (Breunig et al., 2020). ...
Cover crops are a critical agricultural practice that can improve soil quality, enhance crop yields, and reduce nitrogen and phosphorus losses from farms. Yet there is limited understanding of the extent to which cover crops have been adopted across large spatial and temporal scales. Remote sensing offers a low-cost way to monitor cover crop adoption at the field scale and at large spatio-temporal scales. To date, most studies using satellite data have mapped the presence of cover crops, but have not identified specific cover crop species, which is important because cover crops of different plant functional types (e.g., legumes, grasses) perform different ecosystem functions. Here we use Sentinel-2 satellite data and a random forest classifier to map the cover crop species cereal rye and red clover, which represent grass and legume functional types, in the River Raisin watershed in southeastern Michigan. Our maps of agricultural landcover across this region, including the two cover crop species, had moderate to high accuracies, with an overall accuracy of 83%. Red clover and cereal rye achieved F1 scores that ranged from 0.7 to 0.77, and user's and producer's accuracies that ranged from 63.3% to 86.2%. The most common misclassification of cover crops was fallow fields with remaining crop stubble, which often looked similar because these cover crop species are typically planted within existing crop stubble, or interseeded into a grain crop. We found that red-edge bands and images from the end of April and early July were the most important for classification accuracy. Our results demonstrate the potential to map individual cover crop species using Sentinel-2 imagery, which is critical for understanding the environmental outcomes of increasing crop diversity on farms.
... In single-or multi-site studies (<10 fields), high accuracy R 2 of up to 80% could be achieved to predict cover crop biomass or nitrogen content (Biewer et al., 2009;Prabhakara et al., 2015;Xu et al., 2018;Yuan et al., 2019). However, studies across >10 sites are rare and usually have limited accuracy, e.g., R 2 50-73%, on utilizing multispectral sensing for quantifying cover crop biomass (Goffart et al., 2021;Hively et al., 2009;Xia et al., 2021). Such accuracies are partially due to the limitations of multispectral sensing, in particular: (i) limited spectral signatures to detect plant nutrient traits, (ii) scale mismatch with field data from small sampling plots, and (iii) empirical regression lacking scalability and transferability across real-world diversity of field conditions. ...
... Quantifying plant traits in partially vegetation conditions with diverse soil background signals is often challenging. Previous multi-site studies (>10 sites) with multispectral data and environment covariates (e.g., air temperature, growing degree days) can achieve limited accuracies, e.g., R 2 around 50-73%, in predicting cover crop biomass (Goffart et al., 2021;e.g., Hively et al., 2009;Xia et al., 2021). Compared to these studies, this study of using PGML obtained higher accuracies (Fig. 7) of cover crop biomass (relative RMSE = 15.16%) and nitrogen content (relative RMSE = 16.59%) with only remote sensing data as inputs. ...
Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400-2400 nm) to acquire high spatial (0.5 m) and spectral (3-5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R 2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R 2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. We also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.
... Publicly available satellite remote sensing at medium-spatial resolution (10-100 m) provides multispectral information capable of monitoring WCC performance at the field scale (Goffart et al., 2021;Hively et al., 2009Hively et al., , 2015Thieme et al., 2020). The National Aeronautics and Space Administration (NASA) launched Landsat-8 in February 2013, which provides global multispectral observations at 30-m resolution every 16 days through the U.S. Geological Survey (USGS) (Roy et al., 2014;USGS Landsat Missions, 2022). ...
Cover crops are planted to reduce soil erosion, increase soil fertility, and improve watershed management. In the Delmarva Peninsula of the eastern United States, winter cover crops are essential for reducing nutrient and sediment losses from farmland. Cost-share programs have been created to incentivize cover crops to achieve conservation objectives. This program required that cover crops be planted and terminated within a specified time window. Usually, farmers report cover crop termination dates for each enrolled field (∼28,000 per year), and conservation district staff confirm the report with field visits within two weeks of termination. This verification process is labor-intensive and time-consuming and became restricted in 2020–2021 due to the COVID-19 pandemic. This study used Harmonized Landsat and Sentinel-2 (HLS, version 2.0) time-series data and the within-season termination (WIST) algorithm to detect cover crop termination dates over Maryland and the Delmarva Peninsula. The estimated remote sensing termination dates were compared to roadside surveys and to farmer-reported termination dates from the Maryland Department of Agriculture database for the 2020–2021 cover crop season. The results show that the WIST algorithm using HLS detected 94% of terminations (statuses) for the enrolled fields (n = 28,190). Among the detected terminations, about 49%, 72%, 84%, and 90% of remote sensing detected termination dates were within one, two, three, and four weeks of agreement to farmer-reported dates, respectively. A real-time simulation showed that the termination dates could be detected one week after termination operation using routinely available HLS data, and termination dates detected after mid-May are more reliable than those from early spring when the Normalized Difference Vegetation Index (NDVI) was low. We conclude that HLS imagery and the WIST algorithm provide a fast and consistent approach for generating near-real-time cover crop termination maps over large areas, which can be used to support cost-share program verification.
... The many earth observation systems that have been developed include the moderate resolution imaging spectroradiometer (MODIS) and Landsat satellite imagery, which is commonly used for Agricultural applications [19]. The Sentinel-2 satellite developed by the European Space Agency (ESA) as part of the Copernicus program in 2015 carries a multispectral high-resolution instrument (MSI), which has great potential to monitor crop plants at farm scale over agricultural lands [20]. ...
Accurate estimates and predictions of sunflower crop yields at the pixel and field level are critically important for farmers, service dealers, and policymakers. Several models based on remote sensing data have been developed in yield assessment, but their robustness—especially in small field scale areas—needs to be examined. Here we aim to develop a robust methodology for estimation/prediction of sunflower yield at pilot field scale using Sentinel-2 remote sensing satellite imagery. We conducted the study in Mezőhegyes, south-eastern Hungary. The Random Forest Regression (RFR), a machine learning technique was used in this research to translate the Sentinel-2 spectral bands to sunflower yield based on crop yield data provided by a combine harvester equipped with a yield-monitoring system. Sentinel-2 images obtained from April to September were used to find the best image for prediction. The satellite image acquired on June 28 was found best and considered further for prediction sunflower yield. A developed training model was tested and validated in 10 different parcels to evaluate the performance of the prediction. We examined the results of the prediction model (predicted) against the actual yield data (observed) collected by a combine harvester. The results demonstrated that using 10 spectral bands from Sentinel-2 imagery the best time to predict sunflower yields was between 85–105 d into the growing season during the flowering stage. This model achieved high accuracy with low normalized root means square error (RMSE) ranging from 121.9 to 284.5 kg/ha for different test fields. Our results are promising because they prove the possibility of predicting sunflower grain yield at the pixel or field level, 3–4 months before the harvest, which is crucial for planning food policy.
... Our results indicate that the best VI for measuring the aboveground biomass of cereal grass cover crop species is the normalized difference vegetation index calculated using Sentinel-2 red-edge band 5 (NDVI_RE1), supporting our first hypothesis regarding the utility of the red-edge region for the improved biomass estimation of winter cover crops. Our findings are consistent with other studies that observed that the red-edge region was important for estimating crop biophysical characteristics, including LAI, the fraction of absorbed photosynthetically active radiation, fraction of vegetation cover, and biomass [17,19,25,28,29]. The red-edge region is a unique characteristic of healthy vegetation as it links the highly absorptive red region, which is sensitive to chlorophyll, and the highly reflective NIR region, which is linked to plant internal cellular structure [20,76]. ...
The magnitude of ecosystem services provided by winter cover crops is linked to their performance (i.e., biomass associated nitrogen content, forage quality, and fractional ground cover), although few studies quantify these characteristics across the landscape. Remote sensing can produce landscape-level assessments of cover crop performance. However, commonly employed optical vegetation indices (VI) saturate, limiting their ability to measure high-biomass cover crops. Contemporary VIs that employ red-edge bands have been shown to be more robust to saturation issues. Additionally, synthetic aperture radar (SAR) data have been effective at estimating crop biophysical characteristics, although this has not been demonstrated on winter cover crops. We assessed the integration of optical (Sentinel-2) and SAR (Sentinel-1) imagery to estimate winter cover crops biomass across 27 fields over three winter–spring seasons (2018–2021) in Maryland. We used log-linear models to predict cover crop biomass as a function of 27 VIs and eight SAR metrics. Our results suggest that the integration of the normalized difference red-edge vegetation index (NDVI_RE1; employing Sentinel-2 bands 5 and 8A), combined with SAR interferometric (InSAR) coherence, best estimated the biomass of cereal grass cover crops. However, these results were season- and species-specific (R2 = 0.74, 0.81, and 0.34; RMSE = 1227, 793, and 776 kg ha−1, for wheat (Triticum aestivum L.), triticale (Triticale hexaploide L.), and cereal rye (Secale cereale), respectively, in spring (March–May)). Compared to the optical-only model, InSAR coherence improved biomass estimations by 4% in wheat, 5% in triticale, and by 11% in cereal rye. Both optical-only and optical-SAR biomass prediction models exhibited saturation occurring at ~1900 kg ha−1; thus, more work is needed to enable accurate biomass estimations past the point of saturation. To address this continued concern, future work could consider the use of weather and climate variables, machine learning models, the integration of proximal sensing and satellite observations, and/or the integration of process-based crop-soil simulation models and remote sensing observations.
... The many earth observation systems that have been developed include the moderate resolution imaging spectroradiometer (MODIS) and Landsat satellite imagery, which is commonly used for Agricultural applications [19]. The Sentinel-2 satellite developed by the European Space Agency (ESA) as part of the Copernicus program in 2015 carries a multispectral high-resolution instrument (MSI), which has great potential to monitor crop plants at farm scale over agricultural lands [20]. ...
Winter cover crops are planted during the fall to reduce nitrogen losses and soil erosion and improve soil health. Accurate estimations of winter cover crop performance and biophysical traits including biomass and fractional vegetative groundcover support accurate assessment of environmental benefits. We examined the comparability of measurements between ground-based and spaceborne sensors as well as between processing levels (e.g., surface vs. top-of-atmosphere reflectance) in estimating cover crop biophysical traits. This research examined the relationships between SPOT 5, Landsat 7, and WorldView-2 same-day paired satellite imagery and handheld multispectral proximal sensors on two days during the 2012–2013 winter cover crop season. We compared two processing levels from three satellites with spatially aggregated proximal data for red and green spectral bands as well as the normalized difference vegetation index (NDVI). We then compared NDVI estimated fractional green cover to in-situ photographs, and we derived cover crop biomass estimates from NDVI using existing calibration equations. We used slope and intercept contrasts to test whether estimates of biomass and fractional green cover differed statistically between sensors and processing levels. Compared to top-of-atmosphere imagery, surface reflectance imagery were more closely correlated with proximal sensors, with intercepts closer to zero, regression slopes nearer to the 1:1 line, and less variance between measured values. Additionally, surface reflectance NDVI derived from satellites showed strong agreement with passive handheld multispectral proximal sensor-sensor estimated fractional green cover and biomass (adj. R2 = 0.96 and 0.95; RMSE = 4.76% and 259 kg ha−1, respectively). Although active handheld multispectral proximal sensor-sensor derived fractional green cover and biomass estimates showed high accuracies (R2 = 0.96 and 0.96, respectively), they also demonstrated large intercept offsets (−25.5 and 4.51, respectively). Our results suggest that many passive multispectral remote sensing platforms may be used interchangeably to assess cover crop biophysical traits whereas SPOT 5 required an adjustment in NDVI intercept. Active sensors may require separate calibrations or intercept correction prior to combination with passive sensor data. Although surface reflectance products were highly correlated with proximal sensors, the standardized cloud mask failed to completely capture cloud shadows in Landsat 7, which dampened the signal of NIR and red bands in shadowed pixels.
Soil organic matter (SOM), as the greatest carbon storage in the terrestrial environment, is inextricably related to the global carbon cycle and global climate change. Accurate estimation and mapping of SOM content are crucial for guiding agricultural output and management, as well as controlling the climate issue. Traditional chemical analysis is unable to satisfy the dynamic estimation of SOM due to its low timeliness. Remote and proximal sensing have significant advantages in terms of ease of use, estimation accuracy, and geographical resolution. In this study, we developed a framework based on machine learning to estimate SOM with high accuracy and resolution using Fourier mid-infrared attenuation total reflectance spectroscopy (FTIR-ATR), Sentinel-2 images, and DEM derivatives. This framework’s performance was evaluated on a regional scale using 245 soil samples from northeast China. Results indicated that the calibration size could be shrunk to 50% while achieving a fair prediction performance for SOM content. The Lasso, partial least squares (PLS), support vector regression (SVR), and convolutional neural networks (CNN) performed well in predicting SOM from FTIR-ATR spectra, and the performance was enhanced further by using Sentinel-2 images and DEM derivates. The PLS, SVR, and CNN models created SOM maps with higher spatial resolution and variation than the Kriging approach. The PLS and SVR models provided enough variety and were more realistic in the local SOM map, making them usable at the field scale, and the suggested framework took a fresh look at high-resolution SOM mapping.
Cover crops are known to provide beneficial effects to agricultural systems such as a reduction in nitrate leaching, erosion control, and an increase in soil organic matter. The monitoring of cover crops’ growth (e.g., green area index (GAI), nitrogen (N) uptake, or dry matter (DM)) using remote sensing techniques allows us to identify the physiological processes involved and to optimise management decisions. Based on the data of a two-year trial (2018, 2019) in Kiel, Northern Germany, the multispectral sensor Sequoia (Parrot) was calibrated to the selected parameters of the winter cover crops oilseed radish, saia oat, spring vetch, and winter rye as sole cover crops and combined in mixtures. Two simple ratios (SRred, SRred edge) and two normalised difference indices (NDred, NDred edge) were calculated and tested for their predicting power. Furthermore, the advantage of the species/mixture–individual compared to the universal models was analysed. SRred best predicted GAI, DM, and N uptake (R²: 0.60, 0.53, 0.45, respectively) in a universal model approach. The canopy parameters of saia oat and spring vetch were estimated by species–individual models, achieving a higher R² than with the universal model. Comparing mixture–individual models to the universal model revealed low relative error differences below 3%. The findings of the current study serve as a tool for the rapid and inexpensive estimation of cover crops’ canopy parameters that determine environmental services.
