Abdelrazek Elnashar

Road construction significantly affects water resources by introducing contaminants, fragmenting habitats, and degrading water quality. This study examines the use of Remote Sensing (RS) data of Sentinel-1 (S1) and Senitnel-2 (S2) in Google Earth Engine (GEE) to do spatio-temporal analysis of turbidity in adjacent water bodies during the construction and operation of the E18 Arendal-Tvedestrand highway in southeastern Norway from 2017 to 2021. S1 radiometric data helped delineate water extents, while S2-Top of Atmosphere (TOA) multispectral data, corrected using the Modified Atmospheric correction for INland waters (MAIN), used to estimate turbidity levels. To ensure a comprehensive time series of RS data, we utilized S2-TOA data corrected with the MAIN algorithm rather than S2-Bottom Of Atmosphere (BOA) data. We validated the MAIN algorithm's accuracy against GLORIA (Global Observatory of Lake Responses to Interventions and Drivers) observations of surface water reflectance in lakes, globally. Subsequently, the corrected S2 data is used to calculate turbidity using the Novoa and Nechad retrieval algorithms and compared with GLORIA turbidity observations. Findings indicate that the MAIN algorithm adequately estimates water-leaving surface reflectance (Pearson correlation > 0.7 for wavelengths between 490 and 705 nm) and turbidity (Pearson correlation > 0.6 for both algorithms), determining Nechad as the more effective algorithm. In this regard, we used S2 corrected images with MIAN to estimate turbidity in the study area and evaluated with local gauge data and observational reports. Results indicate that the proposed framework effectively captures trends and patterns of turbidity variation in the study area. Findings verify that road construction can increase turbidity in adjacent water bodies and emphasis the employing RS data in cloud platforms like GEE can provide insights for effective long-term water quality management strategies during construction and operation phases.

Road construction significantly affects water resources by introducing contaminants, fragmenting habitats, and degrading water quality. This study examines the use of Remote Sensing (RS) data of Sentinel-1 (S1) and Senitnel-2 (S2) in Google Earth Engine (GEE) to do spatio-temporal analysis of turbidity in adjacent water bodies during the construction and operation of the E18 Arendal-Tvedestrand highway in southeastern Norway from 2017 to 2021. S1 radiometric data helped delineate water extents, while S2-Top of Atmosphere (TOA) multispectral data, corrected using the Modified Atmospheric correction for INland waters (MAIN), used to estimate turbidity levels. To ensure a comprehensive time series of RS data, we utilized S2-TOA data corrected with the MAIN algorithm rather than S2-Bottom Of Atmosphere (BOA) data. We validated the MAIN algorithm's accuracy against GLORIA (Global Observatory of Lake Responses to Interventions and Drivers) observations of surface water reflectance in lakes, globally. Subsequently, the corrected S2 data is used to calculate turbidity using the Novoa and Nechad retrieval algorithms and compared with GLORIA turbidity observations. Findings indicate that the MAIN algorithm adequately estimates water-leaving surface reflectance (Pearson correlation > 0.7 for wavelengths between 490 and 705 nm) and turbidity (Pearson correlation > 0.6 for both algorithms), determining Nechad as the more effective algorithm. In this regard, we used S2 corrected images with MIAN to estimate turbidity in the study area and evaluated with local gauge data and observational reports. Results indicate that the proposed framework effectively captures trends and patterns of turbidity variation in the study area. Findings verify that road construction can increase turbidity in adjacent water bodies and emphasis the employing RS data in cloud platforms like GEE can provide insights for effective long-term water quality management strategies during construction and operation phases.

The increasing reliance on global models for evaluating climate- and human-induced impacts on the hydrological cycle underscores the importance of assessing the models' reliability. Hydrological models provide valuable data on ungauged river basins or basins with limited gauge networks. The objective of this study was to evaluate the reliability of 13 global models using the Gravity Recovery and Climate Experiment (GRACE) satellite's total water storage (TWS) seasonal cycle for 29 river basins in different climate zones. Results show that the simulated seasonal total water storage change (TWSC) does not compare well with GRACE even in basins within the same climate zone. The models overestimated the seasonal peak in most boreal basins and underestimated it in tropical, arid, and temperate zones. In cold basins, the modeled phase of TWSC precedes that of GRACE by up to 2–3 months. However, it lagged behind that of GRACE by 1 month over temperate and arid to semi-arid basins. The phase agreement between GRACE and the models was good in the tropical zone. In some basins with major underlying aquifers, those models that incorporate groundwater simulations provide a better representation of the water storage dynamics. With the findings and analysis of our study, we concluded that R2 (Water Resource Reanalysis tier 2 forced with Multi-Source Weighted Ensemble Precipitation (MSWEP) dataset) models with optimized parameterizations have a better correlation with GRACE than the reverse scenario (R1 models are Water Resource Reanalysis tier 1 and tier 2 forced with the ERA-Interim (WFDEI) meteorological reanalysis dataset). This signifies an enhancement in the predictive capability of models regarding the variability of TWSC. The seasonal peak, amplitude, and phase difference analyses in this study provide new insights into the future improvement of large-scale hydrological models and TWS investigations.

Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data, particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine learning workflow, including automatic training and optimization of multiple models within a user-specified time frame, but it has less attention so far. Here, we combined extensive field survey yield across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to predict field-level wheat yield using 22 Ml models in AutoML. The models showed robust accuracies for yield predictions, recording Willmott degree of agreement, (d > 0.80) with higher accuracy when super learner (stacked ensemble) was used (R2 = 0.51, d = 0.82). The trained AutoML was deployed to predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation with actual yield (R2 = 0.7). This is very important since it is considered a low-cost tool and could be used to explore early yield predictions. Since climate change has negative impacts on agricultural production and food security with some uncertainties, AutoML was deployed to predict wheat yield under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6). These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050). The stacked ensemble model displayed declines in yield of 21% and 5% under SSP5-8.5 and SSP2-4.5 respectively during mid-century, with higher uncertainty under the highest emission scenario (SSP5-8.5). The developed approach could be used as a rapid, accurate and low-cost method to predict yield for stakeholder farms all over the world where ground data is scarce.

Mediterranean drylands are rich in biodiversity and play an important role in global ecosystem sustainable management. This study summarizes the characteristics, dynamic change, and change drivers of Mediterranean drylands. The drylands showed strong spatial heterogeneity, hyperarid and arid regions were dominant in North Africa and West Asia, and semiarid and dry subhumid regions were widely distributed in European countries. Mediterranean dryland is experiencing a warming trend that would become stronger under representative concentration pathways (RCP) 4.5 and 8.5, which would increase the risk of land degradation and desertification. Arid North Africa and West Asia faced rapid population growth that put considerable pressure on food supply and water consumption. The conflicts among land, water, food, and the ecosystem intensified under the warming trend. The significant expansion of cropland and urbanization was widely observed in arid areas, such as Egypt, while the rotation of land reclamation, degradation, abandonment, and reclamation was observed in arid areas and caused large-scale cross-border migration. The Mediterranean region had low food self-sufficiency due to a booming population, and the crop structure of cash crops was dominant. The expansion of cropland also significantly increased the water consumption in the arid area of the Mediterranean region, and water consumption increased by 684.54 × 106 m3 from 2000 to 2020 in Egypt. More robust models and fine spatial resolution data should be developed for the sustainable development of Mediterranean drylands.

Modeling monthly rainfall erosivity is vital to the optimization of measures to control soil erosion. Rain gauge data combined with satellite observations can aid in enhancing rainfall erosivity estimations. Here, we presented a framework which utilized Geographically Weighted Regression approach to model global monthly rainfall erosivity. The framework integrates long-term (2001–2020) mean annual rainfall erosivity estimates from IMERG (Global Precipitation Measurement (GPM) mission’s Integrated Multi-satellitE Retrievals for GPM) with station data from GloREDa (Global Rainfall Erosivity Database, n = 3,286 stations). The merged mean annual rainfall erosivity was disaggregated into mean monthly values based on monthly rainfall erosivity fractions derived from the original IMERG data. Global mean monthly rainfall erosivity was distinctly seasonal; erosivity peaked at ~ 200 MJ mm ha−1 h−1 month−1 in June–August over the Northern Hemisphere and ~ 700 MJ mm ha−1 h−1 month−1 in December–February over the Southern Hemisphere, contributing to over 60% of the annual rainfall erosivity over large areas in each hemisphere. Rainfall erosivity was ~ 4 times higher during the most erosive months than the least erosive months (December–February and June–August in the Northern and Southern Hemisphere, respectively). The latitudinal distributions of monthly and seasonal rainfall erosivity were highly heterogeneous, with the tropics showing the greatest erosivity. The intra-annual variability of monthly rainfall erosivity was particularly high within 10–30° latitude in both hemispheres. The monthly rainfall erosivity maps can be used for improving spatiotemporal modeling of soil erosion and planning of soil conservation measures.

Rapid population growth, climate change, and limited natural resources have widened the gap between food production and consumption, contributing to global hunger. Improving cereal crop production is a critical hot spot challenge for closing this gap and ensuring global food security and nutrition. Previous data and findings from published literature demonstrated that cereal crop models have been applied and developed globally over the last 30 years under a wide range of climate, soil, genotype, and management conditions. However, when the models are applied to pests, diseases, phosphorus fertilization, potassium fertilization, iron, and zinc, further improvements are required. Furthermore, the integration of genotypes and phenotypes is critical for food security, necessitating careful consideration in crop models. We examined about 31 cereal crop models for increasing crop production and ensuring food and nutrition security. Furthermore, we discussed the current limitations in crop model application, as well as the critical need to integrate with other cutting-edge sciences, such as remote sensing, machine learning, and deep learning. This will undoubtedly improve crop model accuracy and reduce uncertainty, assisting agronomists and decision makers in ensuring food and nutrition security. In this chapter, we discussed the current and further improvements of cereal crop models in assisting breeders, researchers, agronomists, and policy makers in addressing current and future challenges related to global food security and nutrition.

Study region
The Nile Delta, Egypt

Study focus
Shallow groundwater (GW) and soil salinity are major issues for irrigated agriculture, particularly in arid and semi-arid regions, but more research is needed to link both issues with evapotranspiration. Satellite-based evapotranspiration from Landsat images (ETLS) has the potential to be an efficient method of estimating evapotranspiration (ET), which can integrate ETLS with groundwater and soil salinity, particularly in data-scarce areas. This study examines shallow GW and soil salinity effects on crop water use in the North Nile Delta during the summer season of 2017 and winter season of 2017/2018.

New hydrological insights for the region
The ETLS was moderately affected by groundwater depth (GWD), decreasing from 4.3 to 4.0 mm day−1 when GWD was reduced from 75 to 120 cm, then increasing to 4.4 mm day−1 when GWD was increased to 140 cm. The study also highlighted a significant negative correlation between ETgw and GWD; which increased with shallower GW (>75 cm) and then decreased with deeper GW. The shallower the GW, the greater the contribution to crop water requirements, with GW contributing 1.6 and 1.7 mm day−1 for seed melon and cotton, respectively, while GW contributed 0.9 mm day−1 for sugar beet and 1.3 mm day−1 for wheat and clover. The study's findings highlight the importance of remote sensing and GIS techniques for quickly and cheaply assessing the impact of shallow GW and soil salinity on evapotranspiration over large geographic areas.

Abstract Wind speed changes impact society and have important implications for climate change studies. Thus, high-resolution and high-quality wind speed datasets are necessary for environmental monitoring and ecosystem research. However, there is no complete set of high spatial and temporal resolution wind speed datasets for China. Additionally, it is extremely challenging to produce wind speed data at high spatial and temporal resolution for large-scale regions with diverse climate types and complex topographies, such as China. In this study, we used multisource remote sensing images, obtained data on various environmental factors through the Google Earth Engine and Evapotranspiration (ET) Watch Cloud platforms, and combined machine learning algorithms to downscale the ERA5 reanalysis wind speed data, and finally obtained the daily wind speed datasets with 1 km spatial resolution for China in 2015. To verify the accuracy of the model and data products, we selected several metrics to evaluate in conjunction with the actual site observed data. The results show that the multifactor combination model of artificial neural network combining land surface temperature, sunshine durations and roughness factors outperforms a single-factor combination model, and the results were in good agreement with the original data (R2 of 0.95 and RMSE of 0.40 m·s−1). The final wind speed data products were also in good agreement with the observed meteorological data (R2 range of 0.86–0.95 and RMSE range of 0.33–0.44 m·s−1); moreover, the accuracy and precision were greatly improved over the original data. This study provided a dataset that has potential applications in future climate change and ecosystem studies.

Recent climate change (CC) scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6) have just been released in coarse resolution. Deep learning (DL) based on statistical downscaling has recently been used, but more research is needed, particularly in arid regions, because little is known about their suitability for extrapolating future CC scenarios. Here we analyzed this issue by downscaling maximum, and minimum temperature over the Egyptian domain based on one General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP4.5 and SSP8.5 from CMIP6 using Convolutional Neural Network (CNN) herein after called CNNSD. The downscaled maximum and minimum temperatures based CNNSD was able to reproduce the observed climate over historical and future periods at a finer resolution (0.1°), reducing the biases exhibited by the original scenario. To the best of our knowledge, this is the first time CNN has been used to downscale CMIP6 scenarios, particularly in arid regions. The downscaled analysis showed that maximum and minimum temperatures are expected to rise by 4.8 °C and 4.0 °C, respectively, in the future (2015–2100), compared to the historical period, under the moderate scenario (SSP4.5). Meanwhile, under the Fossil-fueled Development scenario (SSP8.5), these values will rise by 6.3 °C and 4.2 °C, respectively as analyzed by the CNNSD. The developed approach could be used not only in Egypt but also in other developing countries, which are especially vulnerable to climate change and has a scarcity of related research. The established downscaled approach's supply can be used to provide climate services, as a driver for impact studies and adaptation decisions, and as information for policy development. More research is needed, however, to include multi-GCMs to quantify the uncertainties between GCMs and SSPs, improving the outputs for use in climate change impacts and adaptations for food and nutrition security.

Rainfall erosivity is a key factor that influences soil erosion by water. Rain-gauge measurements are commonly used to estimate rainfall erosivity. However, long-term gauge records with sub-hourly resolutions are lacking in large parts of the world. Satellite observations provide spatially continuous estimates of rainfall, but they are subject to biases that affect estimates of rainfall erosivity. We employed a novel approach to map global rainfall erosivity based on a high-temporal-resolution (30-min), long-term (2001–2020) satellite-based precipitation product—the Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (GPM-IMERG)—and mean annual rainfall erosivity from the Global Rainfall Erosivity Database (GloREDa) stations (n = 3286). We used a residual-based merging scheme to integrate GPM-IMERG-based rainfall erosivity with GloREDa using Geographically Weighted Regression (GWR). The accuracy of the GWR-based merging scheme was evaluated with a 10-fold cross-validation against GloREDa stations. Based on GPM-IMERG-only, the global mean annual rainfall erosivity was estimated to be 1173 MJ mm ha−1 h−1 yr−1 with a standard deviation of 1736 MJ mm ha−1 h−1 yr−1. The mean value estimated via GPM-IMERG merged with GloREDa was 2020 MJ mm ha−1 h−1 yr−1 with a standard deviation of 3415 MJ mm ha−1 h−1 yr−1. Overall, GPM-IMERG-only estimates underestimated rainfall erosivity. The underestimations were greatest in areas of high rainfall erosivity. The accuracy of rainfall erosivity estimates from GPM-IMERG merged with GloREDa substantially improved (Nash-Sutcliffe efficiency = 0.83, percent bias = −2.4%, and root mean square error = 1122 MJ mm ha−1 h−1 yr−1) compared to estimates by GPM-IMERG-only (Nash-Sutcliffe efficiency = 0.51, percent bias = 27.8%, and root mean square error = 1730 MJ mm ha−1 h−1 yr−1). Improving satellite-based global rainfall erosivity estimates through integrating with gauge data is relevant as it can contribute to enhancing soil erosion modeling and, in turn, support land degradation neutrality programs.

Traditional simulation models are often point based; thus, more research is needed to emphasize spatial simulation, providing decision-makers with fast recommendations. Combining machine learning algorithms with spatial process-based models could be considered an appropriate solution. We created a spatial model in R (APSIMx_R) to generate fine-resolution data from coarse-resolution data, which is typically available at the regional level. The APSIM crop model outputs were then deployed to train and test the artificial neural network, creating a hybrid modeling approach for robust spatial simulations. The APSIMx_R package facilitates preparing the required model inputs, executes the prediction, processes, and analyzes the APSIM crop model outputs. This note demonstrates the use of a new approach for creating reproducible crop modeling workflows with the spatial APSIM next-generation model and machine learning algorithms. The tool was deployed for spatial and temporal simulation of potential wheat yield under different nitrogen rates and various wheat cultivars. The spatial APSIMx_R was validated by comparing the simulated yield at 100 kg N ha−1 to the analogues' actual yield at the same grid points, which showed good agreement (d = 0.89) between the spatially predicted and actual yield. The hybrid approach increased such precision, resulting in higher agreement (d = 0.95) with actual yield. When the interaction between cultivars and nitrogen levels was considered, it was found that the novel cultivar Sakha95 is nitrogen voracious, exhibiting a larger drop in yield (65%) under minimal nitrogen treatment (0 kg N ha−1) relative to the potential yield.

Accurate global irrigation information is essential for managing water scarcity and improving food security. However, the mapping of high-resolution irrigation at the global scale is challenging due to the wide range of climate conditions, crop types and phenology, ambiguous and heterogeneous spectral features, and farming practices. Here, a robust method is proposed using irrigation performance under drought stress as a proxy for crop productivity stabilization and crop water consumption. For each irrigation mapping zone (IMZ), dry months in the 2017–2019 period and the driest months in the 2010–2019 period were identified over the growing season. The thresholds of the normalized difference vegetation index (NDVI) in the dry months from 2017 to 2019 and the NDVI deviation (NDVIdev) in the driest month were identified to separate irrigated and rainfed cropland with samples. The final threshold from either the NDVI or the NDVIdev of the IMZ was determined with a higher overall accuracy in separating irrigated and non-irrigated areas. The results show that the global maximum irrigation extent (GMIE) at a 30-m resolution was 23.38% of global cropland in 2010–2019, with an overall accuracy of 83.6% globally and significant regional differences in irrigation proportions ranging from 1.1% in western Africa to 100% in Old World deserts among the 110 IMZs and from 0.4% in Belarus to 80.2% in Pakistan and 100% in Egypt among 45 countries. The study quantitatively distinguished annually and intermittently irrigated regions, which had values of 42% and 58% of global cropland, respectively, by applying indicators. This method, using the NDVI and NDVIdev thresholds, is simple, concrete and reproducible and better for zones with homogeneous weather conditions. The study offers independent, consistent and comparable information for defining the baseline, tracking changes in irrigation infrastructure, and leading future changes in how stakeholders plan and design irrigation systems.

The Bakun-Murum (BM) catchment region of the Rajang River Basin (RRB), Sarawak, Malaysia, has been under severe threat for the last few years due to urbanization, global warming, and climate change. The present study aimed to evaluate the time series analysis and impact assessment of the temperature changes on the vegetation/agricultural lands and the water availability within the BM region. For this purpose, the Landsat data for the past thirty years (1990–2020) were used. Remote sensing techniques for estimating the surface temperatures and variation within the vegetation and water bodies were utilized, and validation was done using on-ground weather stations. Google Earth Engine (GEE) and other RS & GIS tools were used for analyzing the time series trends of land surface temperature (LST), normalized difference vegetation index (NDVI), and normalized difference water index (NDWI). The results exposed an overall rise of 1.06 °C in the annual mean temperatures over the last thirty years. A maximum annual mean NDVI of 0.48 was recorded for 2018 and 2019. The lowest annual mean NDVI (0.27) was observed in 2005. The annual mean NDWI increased to 0.48 in 2018 and 2019, respectively. The statistical correlation results revealed the coefficient of determination (R2) of 0.09 and 0.13 for the annual mean LST and annual mean NDVI and the annual mean LST and annual mean NDWI, respectively. Moreover, the Mann-Kendall trend test for the annual mean temperature series indicates a slightly increasing trend with Sen's slope of 0.03 °C/year. It is found that there is a positive trend in the annual mean rainfall patterns, as Sen's slope indicates a yearly increase of 50.58 mm/year. This study found significant changes in the LST, NDVI, and NDWI of the BM catchment region during the last thirty years, demanding the concerned authorities' instant attention to alleviate the adverse effects of such changes to protect the ecosystem.

This study focuses on an ad hoc machine-learning method for locating archaeological sites in arid environments. Pleiades (P1B) were uploaded to the cloud asset of the Google Earth Engine (GEE) environment because they are not yet available on the platform. The average of the SAR data was combined with the P1B image in the selected study area called Blad Talh at Gafsa, which is located in southern Tunisia. This pre-desert region has long been investigated as an important area of Roman civilization (106 BCE). The results show an accurate probability map with an overall accuracy and Kappa coefficient of 0.93 and 0.91, respectively, when validated with field survey data. The results of this research demonstrate, from the perspective of archaeologists, the capability of satellite data and machine learning to discover buried archaeological sites. This work shows that the area presents more archaeological sites, which has major implications for understanding the archaeological significance of the region. Remote sensing combined with machine learning algorithms provides an effective way to augment archaeological surveys and detect new cultural deposits.

Assessing environmentally sensitive areas (ESA) to desertification and understanding their primary drivers are necessary for applying targeted management practices to combat land degradation at the basin scale. We have developed the MEditerranean Desertification And Land Use framework in the Google Earth Engine cloud platform (MEDALUS-GEE) to map and assess the ESA index at 300 m grids in the Blue Nile Basin (BNB). The ESA index was derived from elaborating 19 key indicators representing soil, climate, vegetation, and management through the geometric mean of their sensitivity scores. The results showed that 43.4%, 28.8%, and 70.4% of the entire BNB, Upper BNB, and Lower BNB, respectively, are highly susceptible to desertification, indicating appropriate land and water management measures should be urgently implemented. Our findings also showed that the main land degradation drivers are moderate to intensive cultivation across the BNB, high slope gradient and water erosion in the Upper BNB, and low soil organic matter and vegetation cover in the Lower BNB. The study presented an integrated monitoring and assessment framework for understanding desertification processes to help achieve land-related sustainable development goals.

Despite its essential importance to various spatial agriculture and environmental applications, the information on actual cropland area and its geographical distribution remain highly uncertain over Africa among remote-sensing products. Each of the African regions has its unique physical and environmental limiting factors to accurate cropland mapping, which leads to high spatial discrepancies among remote sensing cropland products. Since no dataset could cope with all limitations, multiple datasets initially derived from various remote sensing sensors and classification techniques must be integrated into a more accurate cropland product than individual layers. Here, in the current study, four cropland products, produced initially from multiple sensors (e.g. Landsat-8 OLI, Sentinel-2 MSI, and PROBA–V) to cover the period (2015–2017), were integrated based on their cropland mapping accuracy to build a more accurate cropland layer. The four cropland layers’ accuracy was assessed at Agro-ecological zones units via an intensive reference dataset (17,592 samples). The most accurate cropland layer was then identified for each zone to construct the final cropland mask at 30 m resolution for the nominal year of 2016 over Africa. As a result, the new layer was produced in higher cropland mapping accuracy (overall accuracy = 91.64% and cropland’s F-score = 0.75). The layer mapped the African cropland area as 282 Mha (9.38% of the Continent area). Compared to earlier cropland synergy layers, the constructed cropland mask showed a considerable improvement in its spatial resolution (30 m instead of 250 m), mapping quality, and closeness to official statistics (R2 = 0.853 and RMSE = 2.85 Mha). The final layer can be downloaded as described under the “Data Availability Statement” section.

Actual EvapoTranspiration (ET) represents the water consumption in watersheds; distinguishing between natural and anthropogenic contributions to ET is essential for water conservation and ecological sustainability. This study proposed a framework to separate the contribution of natural and anthropogenic factors to ET of human-managed land cover types using the Random Forest Regressor (RFR). The steps include: (1) classify land cover into natural and human-managed land covers and then divide ET, meteorological, topographical, and geographical data into two parts corresponding to natural and human-managed land cover types; (2) construct a natural ET (ETn) prediction model using natural land cover types of ET, and the corresponding meteorological, topographical and geographical factors; (3) the constructed ETn prediction model is used to predict the ETn of human-managed land cover types using the corresponding meteorological, topographical and geographical data as inputs, and (4) derive the anthropogenic ET (ETh) by subtracting the natural ET from the total ET (ETt) for human-managed land cover types. Take 2017 as an example, ETn and ETh for rainfed agriculture, mosaic agriculture, irrigated agriculture, and settlement in Colorado, Blue Nile, and Heihe Basin were separated by the proposed framework, with R2 and NSE of predicted ETn above 0.95 and RB within 1% for all three basins. In the semi-arid Colorado River Basin and arid Heihe Basin, human activities on human-managed land cover types tended to increase ET higher than humid Blue Nile Basin. The anthropogenic contribution to total water consumption is approaching 53.68%, 66.47%, and 6.14% for the four human-managed land cover types in Colorado River Basin, Heihe Bain and Blue Nile Basin, respectively. The framework provides strong support for the disturbance of water resources by different anthropogenic activities at the basin scale and the accurate estimation of the impact of human activities on ET to help achieve water-related sustainable development goals.

Combining machine learning (ML) with dynamic models is recommended by recent research for creating a hybrid approach for robust simulations but has received less attention thus far. Herein, we combined multi- ML algorithms with multi-crop models (CMs) of the DSSAT platform to develop a hybrid approach for wheat yield simulation over 40 years in different locations. The simulation analysis included temperatures (minimum and maximum), solar radiation, and precipitation as important key ecological factors in wheat production that varied across sites and years. Detailed observed datasets of wheat yield from 1981 to 2020 were used for training and testing Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), Random Forest Regressor (RFR), and Support Vector Regressor (SVR) using Google Colaboratory (Colab). Such models were built to create four main approaches, including two approaches as hybrid (CMs-ML) and benchmark (pure ML), as well as two testing methods for each approach such as default (75 % training and 25 % testing) and warmest years (2001, 2006, 2009, 2010, and 2018). In addition to wheat yield simulations, ML approaches were used to identify the important features, improve accuracy, and reduce overfitting. We developed ML approaches by novel cells on the built models (i.e., pure ML and hybrid) to eliminate less important features from permutation. Our results revealed that ANN and RFR outperformed other ML algorithms (SVR and KNN) in wheat yield simulation accuracy. Application of ML algorithms reduced yield change from 31.7 % under DSSAT simulations to 8.1 % and uncertainty from 12.8 % to 7.2 % relative to observed wheat yield over the last four decades (1981–2020). Our novel approach, which includes a hybrid CMs-ML model, cloud computing, and a new permutation tool, could be effectively used for robust crop yield simulation on a regional and global scale, contributing to better aid decision-making strategies.

Accurate and early crop-type maps are essential for agricultural policy development and food production assessment at regional and national levels. This study aims to produce a crop-type map with acceptable accuracy and spatial resolution in northern Mongolia by optimizing the combination of Sentinel-1 (S1) and Sentinel-2 (S2) images with the Google Earth Engine (GEE) environment. A total of three satellite data combination scenarios are set, including S1 alone, S2 alone, and the combination of S1 and S2. In order to avoid the impact of data gaps caused by clouds on crop classification, this study reconstructed the time series of S1 and S2 with a 10-day interval using the median composite method, linear moving interpolation, and Savitzky–Golay (SG) filter. Our results indicated that crop-type classification accuracy increased with the increase in data length to all three data combination scenarios. S2 alone has higher accuracy than S1 alone and the combination of S1 and S2. The crop-type map with the highest accuracy was generated using S2 data from 150 days of the year (DOY) (11 May) to 260 DOY (18 September). The OA and kappa were 0.93 and 0.78, respectively, and the F1-score for spring wheat and rapeseed were 0.96 and 0.80, respectively. The classification accuracy of the crop increased rapidly from 210 DOY (end of July) to 260 DOY (August to mid-September), and then it remained stable after 260 DOY. Based on our analysis, we filled the gap of the crop-type map with 10 m spatial resolution in northern Mongolia, revealing the best satellite combination and the best period for crop-type classification, which can benefit the achievement of sustainable development goals 2 (SDGs2).

Agricultural water appropriation has undergone rapid changes in recent decades, but estimates of global water appropriation have not been updated with the latest data and consistent methods. Documenting these changes is challenging given the heterogeneous water use landscape and the growing influence of human activities worldwide, and this complexity cannot be well addressed with the existing methodology, which is subject to large model uncertainties. Here, a spatial analysis and aggregated method was proposed to quantify and refine estimates of global agricultural water appropriation (GAWA) in terms of consumptive freshwater use, with data derived from Earth observations, independent of estimates from hydrological models. The results show the global water appropriation at the pixel scale, in agroecological zones and in the main water-consuming countries, including global maps of rainfed and irrigated cropland evapotranspiration (ET), net water consumption due to irrigation, natural ET and renewable freshwater resources (RFWR), and indicate that agriculture remains the largest user in terms of both water consumption and withdrawals worldwide, representing 87% of global water consumption, with approximately 60% of global freshwater withdrawals devoted to irrigation circa 2015. The percentage of withdrawals devoted to irrigation has decreased in recent decades when compared to the previous estimate of 70%. The results reveal the actual global crop consumptive use (8053.6 km3/yr) of blue and green water and the total human water consumption (8442 km3/yr), which represents the part of the water cycle affected by human intervention, mainly (95.4%) by agriculture. This study reveals that high-resolution irrigated croplands are essential for accurate estimations of water use appropriation and demonstrates that earth observation-derived data can provide a new understanding of global water use landscape. The study can support decision making in sustaining food and water security, and implementing water-adapted sustainable agricultural policies.

Efficient land and water management require the accurate selection of suitable crops that are compatible with soil and crop water requirements (CWR) in a given area. In this study, twenty soil profiles are collected to represent the soils of the study area. Physical and chemical properties of soil, in addition to irrigation water quality, provided data are utilized by the Agriculture Land Evaluation System for Arid and semi-arid regions (ALES-Arid) to determine crop suitability. University of Idaho Ref-ET software is used to calculate CWR from weather data while the Surface Energy Balance Algorithms for Land Model (SEBAL) is utilized to estimate CWR from remote sensing data. The obtained results show that seasonal weather-based CWR of the most suitable field crops (S1 and S2 classes) ranges from 804 to 1625 mm for wheat and berssem, respectively, and ranges from 778 to 993 mm in the vegetable crops potato and watermelon, respectively, under surface irrigation. Mean daily satellite-based CWR are predicted based on SEBAL ranges between 4.79 and 3.62 mm in Toshka and Abu Simbel areas respectively. This study provides a new approach for coupling ALES-Arid, Ref-ET and SEBAL models to facilitate the selection of suitable crops and offers an excellent source for predicting CWR in arid environments. The findings of this research will help in managing the future marginal land reclamation projects in arid and semi-arid areas of the world.

Food security has become a global concern for humanity with rapid population growth, requiring a sustainable assessment of natural resources. Soil is one of the most important sources that can help to bridge the food demand gap to achieve food security if well assessed and managed. The aim of this study was to determine the soil quality index (SQI) for El Fayoum depression in the Western Egyptian Desert using spatial modeling for soil physical, chemical, and biological properties based on the MEDALUS methodology. For this purpose, a spatial model was developed to evaluate the soil quality of the El Fayoum depression in the Western Egyptian Desert. The integration between Digital Elevation Model (DEM) and Sentinel-2 satellite image was used to produce landforms and digital soil mapping for the study area. Results showed that the study area located under six classes of soil quality, e.g., very high-quality class represents an area of 387.12 km2 (22.7%), high-quality class occupies 441.72 km2 (25.87%), the moderate-quality class represents 208.57 km2 (12.21%), slightly moderate-quality class represents 231.10 km2 (13.5%), as well as, a low-quality class covering an area of 233 km2 (13.60%), and very low-quality class occupies about 206 km2 (12%). The Agricultural Land Evaluation System for arid and semi-arid regions (ALESarid) was used to estimate land capability. Land capability classes were non-agriculture class (C6), poor (C4), fair (C3), and good (C2) with an area 231.87 km2 (13.50%), 291.94 km2 (17%), 767.39 km2 (44.94%), and 416.07 km2 (24.4%), respectively. Land capability along with the normalized difference vegetation index (NDVI) used for validation of the proposed model of soil quality. The spatially-explicit soil quality index (SQI) shows a strong significant positive correlation with the land capability and a positive correlation with NDVI at R2 0.86 (p < 0.001) and 0.18 (p < 0.05), respectively. In arid regions, the strategy outlined here can easily be re-applied in similar environments, allowing decision-makers and regional governments to use the quantitative results achieved to ensure sustainable development.

The global distribution of cropping intensity (CI) is essential to our understanding of agricultural land use management on Earth. Optical remote sensing has revolutionized our ability to map CI over large areas in a repeated and cost-efficient manner. Previous studies have mainly focused on investigating the spatiotemporal patterns of CI ranging from regions to the entire globe with the use of coarse-resolution data, which are inadequate for characterizing farming practices within heterogeneous landscapes. To fill this knowledge gap, in this study, we utilized multiple satellite data to develop a global, spatially continuous CI map dataset at 30 m resolution (GCI30). Accuracy assessments indicated that GCI30 exhibited high agreement with visually interpreted validation samples and in situ observations from the PhenoCam network. We carried out both statistical and spatial comparisons of GCI30 with six existing global CI estimates. Based on GCI30, we estimated that the global average annual CI during 2016–2018 was 1.05, which is close to the mean (1.09) and median (1.07) CI values of the existing six global CI estimates, although the spatial resolution and temporal coverage vary significantly among products. A spatial comparison with two satellite-based land surface phenology products further suggested that GCI30 was not only capable of capturing the overall pattern of global CI but also provided many spatial details. GCI30 indicated that single cropping was the primary agricultural system on Earth, accounting for 81.57 % (12.28×106 km2) of the world's cropland extent. Multiple-cropping systems, on the other hand, were commonly observed in South America and Asia. We found large variations across countries and agroecological zones, reflecting the joint control of natural and anthropogenic drivers on regulating cropping practices. As the first global-coverage, fine-resolution CI product, GCI30 is expected to fill the data gap for promoting sustainable agriculture by depicting worldwide diversity of agricultural land use intensity. The GCI30 dataset is available on Harvard Dataverse: https://doi.org/10.7910/DVN/86M4PO (Zhang et al., 2020).