Search

Agricultural intensification has resulted in the depletion of groundwater resources in many regions of the world. A prime example is Saudi Arabia, which witnessed dramatic agricultural expansion since the 1970s. To explore the influence of policy interventions aimed to better manage water resources, accurate information on the changes in the number and acreage of center-pivot fields is required. To quantify these metrics, we apply a hybrid machine learning framework, consisting of Density-Based Spatial Clustering of Applications with Noise, Convolutional Neural Networks, and Spectral Clustering, to the annual maximum Normalized Differential Vegetation Index maps obtained from Landsat imagery collected between 1990 to 2021. When evaluated against more than 28,000 manually delineated fields, the approach demonstrated producer's accuracies ranging from 83.7% to 94.8% and user's accuracies ranging from 90.2% to 97.9%. The coefficient of determination ( R 2 ) between framework-delineated and manually delineated fields was higher than 0.97. Nationally, we found that most fields pre-dated 1990 (covering 8841 km 2 in that year) and were primarily located within the central regions covering Hail, Qassim, Riyadh, and Wadi ad-Dawasir. A small decreasing trend in field acreage was observed for the period 1990–2010. However, by 2015, the acreage had increased to approximately 33,000 fields covering 9310 km 2 . While a maximum extent was achieved in 2016, recent decreases have seen levels return to pre-1990 levels. The gradual decrease between 1990 to 2010 was related to policy initiatives designed to phase-out wheat, while increases between 2010 to 2015 were linked to fodder crop expansion. There is evidence of an agricultural uptick starting in 2021, which is likely in response to global influences such as the COVID-19 pandemic or the conflict in Ukraine. Overall, this work offers the first detailed assessment of long-term agricultural development in Saudi Arabia, and provides important insights related to production metrics such as crop types, crop water consumption, and crop phenology and the overarching impacts of agricultural policy interventions. [ABSTRACT FROM AUTHOR]

Monitoring leaf Chlorophyll (Chl) in-situ is labor-intensive, limiting representative sampling for detailed mapping of Chl variability at field scales across time. Unmanned aeria-l vehicles (UAV) and hyperspectral cameras provide flexible platforms for observing agricultural systems, overcoming this spatio-temporal sampling constraint. Here, we evaluate a customized machine learning (ML) workflow to retrieve multi-temporal leaf-Chl levels, combining sub-centimeter resolution UAV-hyperspectral imagery (400–1,000 nm) with leaf-level reflectance spectra and SPAD measurements, capturing temporal correlations, selecting relevant predictors, and retrieving accurate results under different conditions. The study is performed within a phenotyping experiment to monitor wild tomato plants' development. Several analyses were conducted to evaluate multiple ML strategies, including: (1) exploring sequential versus retraining learning; (2) comparing insights gained from using 272 spectral bands versus 60 pigment-based vegetation indices (VIs); and (3) assessing six regression methods (linear, partial-least-square regression; PLSR, decision trees, support vector, ensemble trees, and Gaussian process; GPR). Goodness-of-fit (R 2) and accuracy metrics (MAE, RMSE) were determined using training/testing and validation data subsets to assess the models' performance. Overall, while equally good performance was obtained using either PLSR, GPR, or random forest, results show: (1) the retraining strategy improved the ability of most of the approaches to model SPAD-based Chl dynamics; (2) comparative analysis between retrievals and validation data distributions informed the models' ability to capture Chl dynamics through SPAD levels; (3) VI predictors slightly improved R 2 (e.g., from 0.59 to 0.74 units for GPR) and accuracy (e.g., MAE and RMSE differences of up to 2 SPAD units) in specific algorithms; (4) feature importance examined through these methods, revealed strong overlaps between relevant bands and VI predictors, highlighting a few decisive spectral ranges and indices useful for retrieving leaf-Chl levels. The proposed ML framework allows the retrieval of high-quality spatially distributed and multi-temporal SPAD-based chlorophyll maps at an ultra-high pixel resolution (e.g., 7 mm). [ABSTRACT FROM AUTHOR]

Drones, machine learning, phenotype, genotype, remote sensing, unmanned aerial vehicles, Digital agriculture, genome-wide association studies Keywords: Digital agriculture, drones, genome-wide association studies, machine learning, phenotype-genotype, remote sensing, unmanned aerial vehicles. Just as phenotyping of field-grown plants is being significantly enhanced by remote sensing and machine learning, so genotyping is being significantly enhanced by the power of high-throughput sequencing and the rapid proliferation of high-quality genome sequences. On the other hand, the increasing availability of flight-stable and user-friendly unmanned aerial vehicle (UAV) platforms that can be combined with lightweight miniaturized sensors has dramatically expanded the capacity for these types of focused investigations (Mahlein, 2016; Yang et al., 2017). [Extracted from the article]

Very high-resolution satellite imagery from the latest generation commercial platforms provides an unprecedented capacity for imaging the Earth with very high spatial detail. However, these data are generally expensive, particularly if large areas or temporal sequences are required. In recent years, lower quality imagery has been enabled through the launch of constellations of small satellites with short revisit time. In this article, we apply for the first time a statistical approach to downscale and bias-correct these multispectral satellite data using the information contained in a limited training set of very high-resolution images. The technique, based on the direct sampling algorithm, aims at extending the coverage of high-resolution images by sampling data from a training data set, where similar lower resolution data patterns are found. Unlike the majority of the current downscaling techniques, the approach does not require colocated fine-resolution data, but it is based on the use of training images similar to the target zone. A novel specific setup is proposed, which is adaptive to different types of landscapes with no additional user effort. The results show that the proposed technique can generate more realistic images than the traditional approaches based on the parametric bias correction and bicubic interpolation. In particular, properties such as the intensity histogram, spatial correlation, and connectivity are accurately preserved. The proposed approach can be used to extend the footprint of the high-resolution images to generate new time frames or to downscale the remote sensing imagery based on a distant but structurally similar training image. [ABSTRACT FROM AUTHOR]

A global beach litter assessment is challenged by use of low-efficiency methodologies and incomparable protocols that impede data integration and acquisition at a national scale. The implementation of an objective, reproducible and efficient approach is therefore required. Here we show the application of a remote sensing based methodology using a test beach located on the Saudi Arabian Red Sea coastline. Litter was recorded via image acquisition from an Unmanned Aerial Vehicle, while an automatic processing of the high volume of imagery was developed through machine learning, employed for debris detection and classification in three categories. Application of the method resulted in an almost 40 times faster beach coverage when compared to a standard visual-census approach. While the machine learning tool faced some challenges in correctly detecting objects of interest, first classification results are promising and motivate efforts to further develop the technique and implement it at much larger scales. [ABSTRACT FROM AUTHOR]

With an increasing volume and dimensionality of Earth observation data, enhanced integration of machine-learning methodologies is needed to effectively analyze and utilize these information rich datasets. In machine-learning, a training dataset is required to establish explicit associations between a suite of explanatory ‘predictor’ variables and the target property. The specifics of this learning process can significantly influence model validity and portability, with a higher generalization level expected with an increasing number of observable conditions being reflected in the training dataset. Here we propose a hybrid training approach for leaf area index (LAI) estimation, which harnesses synergistic attributes of scattered in-situ measurements and systematically distributed physically based model inversion results to enhance the information content and spatial representativeness of the training data. To do this, a complimentary training dataset of independent LAI was derived from a regularized model inversion of RapidEye surface reflectances and subsequently used to guide the development of LAI regression models via Cubist and random forests (RF) decision tree methods. The application of the hybrid training approach to a broad set of Landsat 8 vegetation index (VI) predictor variables resulted in significantly improved LAI prediction accuracies and spatial consistencies, relative to results relying on in-situ measurements alone for model training. In comparing the prediction capacity and portability of the two machine-learning algorithms, a pair of relatively simple multi-variate regression models established by Cubist performed best, with an overall relative mean absolute deviation (rMAD) of ∼11%, determined based on a stringent scene-specific cross-validation approach. In comparison, the portability of RF regression models was less effective (i.e., an overall rMAD of ∼15%), which was attributed partly to model saturation at high LAI in association with inherent extrapolation and transferability limitations. Explanatory VIs formed from bands in the near-infrared (NIR) and shortwave infrared domains (e.g., NDWI) were associated with the highest predictive ability, whereas Cubist models relying entirely on VIs based on NIR and red band combinations (e.g., NDVI) were associated with comparatively high uncertainties (i.e., rMAD ∼ 21%). The most transferable and best performing models were based on combinations of several predictor variables, which included both NDWI- and NDVI-like variables. In this process, prior screening of input VIs based on an assessment of variable relevance served as an effective mechanism for optimizing prediction accuracies from both Cubist and RF. While this study demonstrated benefit in combining data mining operations with physically based constraints via a hybrid training approach, the concept of transferability and portability warrants further investigations in order to realize the full potential of emerging machine-learning techniques for regression purposes. [ABSTRACT FROM AUTHOR]

A regularized canopy reflectance model (REGFLEC) is applied over a dryland irrigated agricultural system in Saudi Arabia for the purpose of retrieving leaf area index (LAI) and leaf chlorophyll content (Chl l ). To improve the robustness of the retrieved properties, REGFLEC was modified to 1) correct for aerosol and adjacency effects, 2) consider foliar dust effects on modeled canopy reflectances, 3) include spectral information in the red-edge wavelength region, and 4) exploit empirical LAI estimates in the model inversion. Using multi-spectral RapidEye imagery allowed Chl l to be retrieved with a Mean Absolute Deviation (MAD) of 7.9 μg cm − 2 (16%), based upon in-situ measurements conducted in fields of alfalfa, Rhodes grass and maize over the course of a growing season. LAI and Chl l compensation effects on canopy reflectance were largely avoided by informing the inversion process with ancillary LAI inputs established empirically on the basis of a statistical machine learning technique. As a result, LAI was reproduced with good accuracy, with an overall MAD of 0.42 m 2 m − 2 (12.5%). Results highlighted the considerable challenges associated with the translation of at-sensor radiance observations to surface bidirectional reflectances in dryland environments, where issues such as high aerosol loadings and large spatial gradients in surface reflectance from bright desert soils to dark vegetated fields are often present. Indeed, surface reflectances in the visible bands were reduced by up to 60% after correction for such adjacency effects. In addition, dust deposition on leaves required explicit modification of the reflectance sub-model to account for its influence. By implementing these model refinements, REGFLEC demonstrated its utility for within-field characterization of vegetation conditions over the challenging landscapes typical of dryland agricultural regions, offering a means through which improvements can be made in the management of these globally important systems. [ABSTRACT FROM AUTHOR]

High spatial and temporal resolution satellite imagery are essential data for land cover discrimination and mapping of vegetation dynamics, offering insights into the number, extent, and condition of agricultural fields. However, an accurate account of the number, location, and variability of fields can be challenging to obtain in a timely manner, particularly at scale or in regions where ground-supporting data are not available, limiting the capacity for food production and water use assessment and planning. To bridge this capacity gap, a convolutional neural network approach was adopted and combined with two clustering techniques: the density-based spatial clustering of applications with noise (DBSCAN) and spectral clustering, to provide an account of agricultural fields and their extent across a region lacking ground based information. A random forest classification was also employed to discriminate crop types. Using an annual maximum normalized difference vegetation index (NDVI) derived from 2018 Landsat-8 data, the approach was applied to classify the shape and delineate the extent of agricultural fields across an agricultural region in Saudi Arabia that had an area under irrigation exceeding 2,300 km2. When assessed against manually identified center-pivot fields (CPFs), the method achieved 97.4% producer's and 98.0% user's accuracies on an object basis, and 81.4% producer's and 85.4% user's accuracies on a pixel basis for identifying non-CPFs (i.e., tree crop plantations and other non-woody crops). The over- and under-segmentation error for CPFs was 1.5% and 1.0%, respectively, with intersection over union errors reported as being 3.5%. The framework showed stability when retrospectively applied to Landsat data from the year 2000, returning 97.5% producer's and 96.6% user's accuracies for CPF identification. In order to characterize the temporal dynamics of agricultural development over the past three decades, an analysis of field behavior between 1988 and 2020 was subsequently undertaken. The analysis indicated that the number of CPFs in the study region increased from 45 (covering 20 km2) in 1988 to 5,080 CPFs by 2016 (covering 2,368 km2), followed by a recent reduction to 3,700 CPFs in 2020 (covering 1,581 km2). Through the multi-temporal analysis, individual fields were able to be characterized in terms of their expansion, contraction and activity throughout the study period. Overall, the proposed method was simple to train, efficient in dealing with large datasets, relied on limited in-situ records to a very small degree, and has the potential to be applied to larger national scales, providing an ongoing assessment of important agroinformatic metrics. [ABSTRACT FROM AUTHOR]

Developing rapid and non-destructive methods for chlorophyll estimation over large spatial areas is a topic of much interest, as it would provide an indirect measure of plant photosynthetic response, be useful in monitoring soil nitrogen content, and offer the capacity to assess vegetation structural and functional dynamics. Traditional methods of direct tissue analysis or the use of handheld meters, are not able to capture chlorophyll variability at anything beyond point scales, so are not particularly useful for informing decisions on plant health and status at the field scale. Examining the spectral response of plants via remote sensing has shown much promise as a means to capture variations in vegetation properties, while offering a non-destructive and scalable approach to monitoring. However, determining the optimum combination of spectra or spectral indices to inform plant response remains an active area of investigation. Here, we explore the use of a machine learning approach to enhance the estimation of leaf chlorophyll (Chlt), defined as the sum of chlorophyll a and b, from spectral reflectance data. Using an ASD FieldSpec 4 Hi-Res spectroradiometer, 2700 individual leaf hyperspectral reflectance measurements were acquired from wheat plants grown across a gradient of soil salinity and nutrient levels in a greenhouse experiment. The extractable Chlt was determined from laboratory analysis of 270 collocated samples, each composed of three leaf discs. A random forest regression algorithm was trained against these data, with input predictors based upon (1) reflectance values from 2102 bands across the 400–2500 nm spectral range; and (2) 45 established vegetation indices. As a benchmark, a standard univariate regression analysis was performed to model the relationship between measured Chlt and the selected vegetation indices. Results show that the root mean square error (RMSE) was significantly reduced when using the machine learning approach compared to standard linear regression. When exploiting the entire spectral range of individual bands as input variables, the random forest estimated Chlt with an RMSE of 5.49 µg·cm−2 and an R2 of 0.89. Model accuracy was improved when using vegetation indices as input variables, producing an RMSE ranging from 3.62 to 3.91 µg·cm−2, depending on the particular combination of indices selected. In further analysis, input predictors were ranked according to their importance level, and a step-wise reduction in the number of input features (from 45 down to 7) was performed. Implementing this resulted in no significant effect on the RMSE, and showed that much the same prediction accuracy could be obtained by a smaller subset of indices. Importantly, the random forest regression approach identified many important variables that were not good predictors according to their linear regression statistics. Overall, the research illustrates the promise in using established vegetation indices as input variables in a machine learning approach for the enhanced estimation of Chlt from hyperspectral data. [ABSTRACT FROM AUTHOR]

• Multi-indicators were jointly used for maize yield estimation. • Random Forest algorithm had a good performance in estimating maize yield. • Surface temperature had the best accuracy among single indicator in estimating yield. • The yield can be predicted within 24 d before maturity with a good accuracy. • More informative indicators can improve the spatial adaptability of the model. The accurate and timely prediction of crop yield at a large scale is important for food security and the development of agricultural policy. An adaptable and robust method for estimating maize yield for the entire territory of China, however, is currently not available. The inherent trade-off between early estimates of yield and the accuracy of yield prediction also remains a confounding issue. To explore these challenges, we employ indicators such as GPP, ET, surface temperature (Ts), LAI, soil properties and maize phenological information with random forest regression (RFR) and gradient boosting decision tree (GBDT) machine learning approaches to provide maize yield estimates within China. The aims were to: (1) evaluate the accuracy of maize yield prediction obtained from multimodal data analysis using machine-learning; (2) identify the optimal period for estimating yield; and (3) determine the spatial robustness and adaptability of the proposed method. The results can be summarized as: (1) RFR estimated maize yield more accurately than GBDT; (2) Ts was the best single indicator for estimating yield, while the combination of GPP, Ts, ET and LAI proved best when multi-indicators were used (R 2 = 0.77 and rRMSE = 16.15% for the RFR); (3) the prediction accuracy was lower with earlier lead time but remained relatively high within at least 24 days before maturity (R 2 > 0.77 and rRMSE <16.92%); and (4) combining machine-learning algorithms with multi-indicators demonstrated a capacity to cope with the spatial heterogeneity. Overall, this study provides a reliable reference for managing agricultural production. [ABSTRACT FROM AUTHOR]

• A first of its kind demonstration of sub-daily high resolution SkySat monitoring. • Dye plume extent could be mapped from SkySat data using object-based detection. • A random forest method could predict dye concentration from SkySat data. • Sub-daily SkySat data could accurately track dye plume extent and concentration. • UAV data bridged the spatial and temporal disconnect between field and SkySat data. Sub-daily tracking of dynamic features and events using high spatial resolution satellite imagery has only recently become possible, with advanced observational capabilities now available through tasking of satellite constellations. Here, we provide a first of its kind demonstration of using sub-daily 0.50 m resolution SkySat imagery to track coastal water flows, combining these data with object-based detection and a machine-learning approach to map the extent and concentration of two dye plumes. Coincident high-frequency unmanned aerial vehicle (UAV) imagery was also employed for quantitative modeling of dye concentration and evaluation of the sub-daily satellite-based dye tracking. Our results show that sub-daily SkySat imagery can track dye plume extent with low omission (8.73–16.05%) and commission errors (0.32–2.77%) and model dye concentration (coefficient of determination = 0.73; root mean square error = 28.68 ppb) with the assistance of high-frequency UAV data. The results also demonstrate the capabilities of using UAV imagery for scaling between field data and satellite imagery for tracking coastal water flow dynamics. This research has implications for monitoring of water flows and nutrient or pollution exchange, and it also demonstrates the capabilities of higher temporal resolution satellite data for delivering further insights into dynamic processes of coastal systems. [Display omitted] [ABSTRACT FROM AUTHOR]