The impact of climate changes on the water footprint of wheat and maize production in the Nile Delta, Egypt

Changes in climate attributes and harvest area structures jointly determined spatial-temporal variations in water footprint of maize in the Beijing-Tianjin-Hebei region

Irrigation contributes significantly to boosting crop yield and ensuring food security. However, in the Beijing-Tianjin-Hebei (BTH) region, unsustainable irrigation practices have led to serious outcomes on freshwater resources. Balancing irrigation with crop productivity in this region, currently facing complex challenge, requires a comprehensive understanding of its spatial pattern and thus to seeking for potential optimization of current crop structures. In this study, we employed the concept of water footprint (WFP) to assess the spatial-temporal patterns of water footprint for maize in BTH region at the county level for the years 2005, 2010, 2015, and 2020, untangled the relative impacts on WFP from climate attributes and harvest area structures. Our results showed significant regional heterogeneities in both blue water requirement and green water requirement, ranging from 64.6 mm to 290.7 mm. Yearly anomalies of climate attributes and maize harvest jointly influenced water footprints, with the highest value of 1.06 × 1011 m3 occurring in the year 2015. The green water footprints, linked to precipitation, dominated the total water footprint compared to the blue water footprint associated with irrigation. Additionally, we observed an increasing influence of maize harvest area on the temporal changes in water footprints, with these changes becoming more concentrated in the east-central region over time. Our findings underscore the respective contributions of annual climate attribute changes and harvest area variations at the county level, highlighting regions where urgent interventions are required to enhance the sustainability of water usage for agriculture.

Prediction of weighted arithmetic water quality index for urban water quality using ensemble machine learning model

Urban water quality index (WQI) is an important factor for assessment quality of groundwater in the urban and rural area. In this research, the Weighted Arithmetic Water Quality Index (WA-WQI) was estimated for understanding the groundwater quality. Four machine learning (ML) models were developed including artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XG-Boost) in addition to multiple linear regression (MLR) for WA-WQI prediction at the Ujjain city of Madhya Pradesh in India. Groundwater quality samples were collected from 54 wards under the urban area, the main eight different physiochemical parameters were selected for WA-WQI prediction. The different input parameters data were analysed and calculated for the relationships of their ability to predict the results of WA-WQI. The ML models performance were calculated using three statistical metrics such as determination coefficient (R2), mean absolute error (MAE), and root mean square error (RMSE). In this research shown the XG-Boost model is better results other than other ML models. The best modelling results over the training phase revealed R2 = 0.969, RMSE = 2.169, MAE = 2.013 and over the testing phase R2 = 0.987, RMSE = 3.273, MAE = 2.727). All the ML models results were validated using receiver operating characteristic (ROC) curve for the best models selection. The results of best model area under curve (AUC) was 0.9048. Hence, XG-Boost model was given the accurate prediction of WA-WQI in the urban area. Based on the graphical presentation evaluation, XG-Boost model showed similar results of superiority. The obtained modelling results emphasis the utility of computer aid models for better planning and essential information for decision-makers, and water experts. The implement agency can adopt the procedures of water quality to decrease pollution and safe and healthy water provide to entire Ujjain city.

Air pollution trend in Chandigarh during 2019-2022: status and influence of meteorological factors

The degradation of ambient air quality is a pressing global concern, and India, as a developing nation, has witnessed a rapid surge in industrial activities in recent decades. This surge has resulted in numerous Indian cities ranking among the world's most polluted urban areas. Chandigarh, strategically positioned within the Indo-Gangetic plains (IGP), has not escaped this distressing trend, experiencing a significant spike in air pollution levels. This study focuses on comprehending and addressing the air quality issues in Chandigarh, shedding light on the evolution of air pollution trends and their dependence on meteorological factors. Notably, the study reveals that, with the exception of O3, pollutant concentrations surge during the rice stubble burning season. These pollutants persist in the atmosphere for prolonged periods, exacerbating the situation during winter due to lower temperatures and heightened use of fossil fuels for heating by low-income households. In contrast, the wheat stubble burning period does not significantly impact pollutant concentrations. The study also identifies a spring peak in surface O3 concentrations, attributed to favorable high temperatures that promote the photochemical reactions responsible for this phenomenon, a distinctive feature in South Asia and the Himalayas. An examination of the connection between pollutant concentrations and meteorological parameters underscores that elevated pollutant levels, except for CO, are linked to lower relative humidity and temperatures. This suggests that current development patterns have contributed to the escalation of air pollution in Chandigarh, necessitating urgent interventions to preserve the city's aesthetics and the health of its residents. Furthermore, to model and monitor pollutant behavior in Chandigarh, more extensive and extended studies are imperative. Both short-term and long-term investigations into the environmental and health impacts of air pollutants, including primary and secondary pollutants, are of paramount importance. These endeavors are essential for the well-being of both the environment and the population of Chandigarh.

Identification of influential weather parameters and seasonal drought prediction in Bangladesh using machine learning algorithm

Droughts pose a severe environmental risk in countries that rely heavily on agriculture, resulting in heightened levels of concern regarding food security and livelihood enhancement. Bangladesh is highly susceptible to environmental hazards, with droughts further exacerbating the precarious situation for its 170 million inhabitants. Therefore, we are endeavouring to highlight the identification of the relative importance of climatic attributes and the estimation of the seasonal intensity and frequency of droughts in Bangladesh. With a period of forty years (1981-2020) of weather data, sophisticated machine learning (ML) methods were employed to classify 35 agroclimatic regions into dry or wet conditions using nine weather parameters, as determined by the Standardized Precipitation Evapotranspiration Index (SPEI). Out of 24 ML algorithms, the four best ML methods, ranger, bagEarth, support vector machine, and random forest (RF) have been identified for the prediction of multi-scale drought indices. The RF classifier and the Boruta algorithms shows that water balance, precipitation, maximum and minimum temperature have a higher influence on drought intensity and occurrence across Bangladesh. The trend of spatio-temporal analysis indicates, drought intensity has decreased over time, but return time has increased. There was significant variation in changing the spatial nature of drought intensity. Spatially, the drought intensity shifted from the northern to central and southern zones of Bangladesh, which had an adverse impact on crop production and the livelihood of rural and urban households. So, this precise study has important implications for the understanding of drought prediction and how to best mitigate its impacts. Additionally, the study emphasizes the need for better collaboration between relevant stakeholders, such as policymakers, researchers, communities, and local actors, to develop effective adaptation strategies and increase monitoring of weather conditions for the meticulous management of droughts in Bangladesh.

Performance analyses of effective rainfall estimation methods for accurate quantification of agricultural water footprint

Water footprint (WF) assessments have become a significant tool for the sustainable management in recent years. Effective rainfall (P_eff) is a critical indicator for characterizing soil moisture (green water, WF_green) and calculating irrigation requirements (blue water, WF_blue). However, majority of the water footprint analyses employ empirical or numerical models to predict P_eff, and the number of studies for experimental validation of these models are quite insufficient. The main scope of this study is to test the performance of commonly used P_eff estimation models in relation to the soil water balance (SWB) of an experimental site. Accordingly, the daily and monthly soil water budget is estimated from a maize field which is characterized as semi-arid land with continental climate (Ankara, Turkey), equipped with moisture sensors. Then, P_eff, WF_green, and WF_blue parameters are calculated using FP, US-BR, USDA-SCS, FAO/AGLW, CROPWAT, and SuET methods and compared with SWB method. Employed models were highly variable. CROPWAT and US-BR predictions were the most accurate. In majority of months, the CROPWAT method estimated the P_eff with a maximum deviation of 5% from the SWB method. In addition, the CROPWAT method predicted blue WF with an error less than 1%. The widely utilized USDA-SCS approach did not produce expected results. The FAO-AGLW method provided the lowest performance for each parameter. We also find that the errors in estimating P_eff in semi-arid conditions cause green and blue WF outputs to be quite less accurate than the dry and humid cases. This study provides one of the most detailed assessments about the impact of effective rainfall on the blue and green WF results with high temporal resolution. The findings of this study are important for the accuracy and performance of the formulae used in P_eff estimations and to develop more precise blue and green WF analyses in the future.

Projection of temperature extremes of Egypt using CMIP6 GCMs under multiple shared socioeconomic pathways

Global warming has amplified the frequency of temperature extremes, especially in hot dry countries, which could have serious consequences for the natural and built environments. Egypt is one of the hot desert climate regions that are more susceptible to climate change and associated hazards. This study attempted to project the changes in temperature extremes for three Shared Socioeconomic Pathways (SSPs), namely, SSP1-2.6, SSP2-4.5, and SSP5-8.5 and two future periods (early future: 2020-2059 and late future: 2060-2099) by using daily maximum (T_max) and minimum temperature (T_min) of general circulation model (GCMs) of Coupled Model Inter-comparison Project phase 6 (CMIP6). The findings showed that most temperature extreme indices would increase especially by the end of the century. In the late future, the change in the mean T_min (4.3 °C) was projected to be higher than the mean T_max (3.7 °C). Annual maximum T_max, temperature above 95th percentile of T_max, and the number of hot days above 40 °C and 45 °C were projected to increase in the range 3.0‒5.4 °C, 1.5‒4.8 °C, 20‒95 days, and 10‒52 days, respectively. In contrast, the annual minimum of T_min, temperature below the 5th percentile, and the annual percentage of cold nights were projected to change in the range of 2.95‒5.0 °C, 1.4‒3.6 °C, and - 0.1‒0.1%, respectively. In all the cases, the lowest changes would be for SSP1-2.6 in the early period and the greatest changes for SSP5-8.5 in the late period. The study indicates that the country is likely to experience a rise in hot extremes and a decline in cold extremes. Therefore, Egypt should take long-term adaptation plans to build social resiliency to rising hot extremes.

Impacts of climate change on water footprint components of rainfed and irrigated wheat in a semi-arid environment

Climate change is one of the biggest environmental challenges that significantly impact water resources and the quantity and quality of agricultural products. Assessment of these impacts during the historical period and under future climate is essential for achieving a sustainable agricultural system in the face of climate change threats and water scarcity. In this research, we evaluated the yield and water footprint of rainfed and irrigated wheat during the historical period (1986-2015) and two future periods (2016 to 2055) in a semi-arid environment in Fars province, Iran. The future climate data was selected from the CanESM2 model outputs (bias-corrected and downscaled using the SDSM model) under the RCP4.5 scenario, and the yield projection was made using the AquaCrop model. Our result showed that for both irrigated and rainfed wheat, the yield significantly increases in southern parts of the study area in future climates, primarily because of an increase in effective precipitation. Other regions will experience a marginal yield decrease or no yield changes (in the case of irrigated wheat). Our assessments of the water footprint of wheat production showed a significant reduction in green and blue water footprints in the southern regions. In other regions, various patterns emerged for irrigated and rainfed wheat, but an overall increase was observed. The southern regions of the study area will be more suitable for wheat production owing to the higher yield and lower water footprint.

Patterns and driving forces of the agricultural water footprint of Chinese cities

The patterns and determinants of different types of agricultural water footprints in China are poorly understood at the prefecture-city level. In this paper, we evaluate Chinese agricultural water footprints from 2000 to 2017 and analyzed their spatio-temporal characteristics. Our estimation results show that the annual average agricultural water footprint in China was 5.038 × 10⁹ m³, and the proportions of green water, blue water, and gray water were 70%, 9%, and 21%, respectively. In addition, high agricultural water-footprint cities with obvious urban agglomeration effects are mainly located in the Northeast, the Huanghuai River, the Yangtze River Basin, and Northwestern of Xinjiang, while low agricultural water-footprint cities are concentrated in high coastal urbanization-level areas or less developed agricultural areas of the west. We also investigate their determinants using a spatio-temporal fixed-effect model and find that GDP per capita, total investment in fixed assets, the income level of rural residents, the proportion of food grown, spray and drip irrigation technology, low-pressure pipe irrigation technology and seepage control irrigation technology have significant positive impacts on the agricultural water footprint. In contrast, the proportion of secondary and tertiary industries, social retail consumption, urbanization, technology expenditure, and the effective irrigation area proportion have a significant inhibitory effect. The primary determinants of the agricultural water footprint also vary substantially across water footprint categories (green, blue, and gray water footprints) and regions. Our findings imply that the agricultural water footprint should be incorporated into city water resource management and monitoring system.

Spatiotemporal Dynamics of Grasslands Using Landsat Data in Livestock Micro-Watersheds in Amazonas (NW Peru)

In Peru, grasslands monitoring is essential to support public policies related to the identification, recovery and management of livestock systems. In this study, therefore, we evaluated the spatial dynamics of grasslands in Pomacochas and Ventilla micro-watersheds (Amazonas, NW Peru). To do this, we used Landsat 5, 7 and 8 images and vegetation indices (normalized difference vegetation index (NDVI), enhanced vegetation index (EVI) and soil adjusted vegetation index (SAVI). The data were processed in Google Earth Engine (GEE) platform for 1990, 2000, 2010 and 2020 through random forest (RF) classification reaching accuracies above 85%. The application of RF in GEE allowed surface mapping of grasslands with pressures higher than 85%. Interestingly, our results reported the increase of grasslands in both Pomacochas (from 2457.03 ha to 3659.37 ha) and Ventilla (from 1932.38 ha to 4056.26 ha) micro-watersheds during 1990–2020. Effectively, this study aims to provide useful information for territorial planning with potential replicability for other cattle-raising regions of the country. It could further be used to improve grassland management and promote semi-extensive livestock farming.

Impact of Climate Change on the Yield and Water Footprint of Winter Wheat in the Haihe River Basin, China

Climate change can impact the yield and water footprint of crops. Therefore, assessing such impacts carries great significance for regional water and food security. This study validated and verified the variety parameters of winter wheat for the Decision Support System for Agrotechnology Transfer (DSSAT) model, using the long-term (1993–2013) growth and yield data observed from six agricultural experiment stations in the Haihe River Basin (HRB), China. The growth process was simulated under three representative concentration pathways (RCPs), named RCP2.6, RCP4.5, and RCP8.5—climate scenarios driven by the HadGEM2-ES model. The variety parameters of winter wheat showed high accuracy in the simulation of the anthesis and maturity dates, and could be used for long-term prediction of the growth process. The trends of climate change had positive impacts on the water footprint of winter wheat but adverse impacts on the yield. The growing period was shortened by 3.6 days, 4.7 days, and 5.0 days per decade in the RCP2.6, RCP4.5, and RCP8.5 scenarios, respectively, due to the rapid accumulation of heat. The yield would be increased in lower emissions scenarios (17% in RCP2.6), but decreased in high-emissions scenarios due to high temperatures, which may restrict the growth of wheat. The water footprint was decreased by 10%, 11%, and 13% in the RCP2.6, RCP4.5, and RCP8.5 scenarios, respectively, indicating that the water-use efficiency could be improved in the future. The results showed broad application prospects of the DSSAT model in simulating the response of crop growth to climate change.

Applications of various data-driven models for the prediction of groundwater quality index in the Akot basin, Maharashtra, India

Data-driven models are important to predict groundwater quality which is controlling human health. The water quality index (WQI) has been developed based on the physicochemical parameters of water samples. In this area, water quality is medium to poor and is found in saline zones; very high pH ranges are directly affected on the water quality in this study area. Conventional WQI computation demands more time and is often observed with enormous errors during the calculation of sub-indices. In the present work, four standalone methods such as additive regression (AR), M5P tree model (M5P), random subspace (RSS), and support vector machine (SVM) were employed to predict WQI based on variable elimination technique. The groundwater samples were collected from the Akot basin area, located in the Akola district, Maharashtra, in India. A total of nine different input combinations were developed in this study. The datasets were demarcated into two classes (ratio 80:20) for model construction (training dataset) and model verification (testing dataset) using a fivefold cross-validation approach. The models were assessed using statistical and graphical appraisal metrics. The best input combinations varied among the model, generally, the optimal input variables (EC, pH, TDS, Ca, Mg, and Cl) during the training and validation stages. Results show that AR outperformed the other data-driven models (R2 = 0.9993, MAE = 0.5243, RMSE = 0.0.6356, %RAE = 3.8449, and RRSE% = 3.9925). The AR is proposed as an ideal model with satisfactory results due to enhanced prediction precision with the minimum number of input parameters and can thus act as the reliable and precise method in the prediction of WQI at the Akot basin.

Modelling the reference crop evapotranspiration in the Beas-Sutlej basin (India): an artificial neural network approach based on different combinations of meteorological data

Accurate prediction of the reference evapotranspiration (ET₀) is vital for estimating the crop water requirements precisely. In this study, we developed multi-layer perceptron artificial neural network (MLP-ANN) models considering different combinations of the meteorological data for predicting the ET₀ in the Beas-Sutlej basin of Himachal Pradesh (India). Four climatic locations in the basin namely, Kullu, Mandi, Bilaspur, and Chaba were selected. The meteorological dataset comprised air temperature (maximum, minimum and mean), relative humidity, solar radiation, and wind speed, recorded daily for a period of 35 years (1984-2019). The datasets from 1984 to 2012 and 2013 to 2019 were utilized for training and testing the models, respectively. The performance of the developed models was evaluated using several statistical indices. For each location, the best performed MLP-ANN model was the one with the complete combination of the meteorological data. The architecture of the best performing model for Kullu, Mandi, Bilaspur, and Chaba was (6-2-4-1), (6-5-4-1), (6-5-4-1), and (6-4-6-1), respectively. It was observed, however, that the performance of other models was also relatively good, given the limited meteorological data utilized in those models. Further, to appreciate the relative predictive ability of the developed models, a comparison was performed with four existing established empirical models. The approach adopted in this study can be effectively utilized by water users and field researchers for modelling and predicting ET₀ in data-scarce locations.

Using Machine Learning Models to Predict Hydroponically Grown Lettuce Yield

Prediction of crop yield is an essential task for maximizing the global food supply, particularly in developing countries. This study investigated lettuce yield (fresh weight) prediction using four machine learning (ML) models, namely, support vector regressor (SVR), extreme gradient boosting (XGB), random forest (RF), and deep neural network (DNN). It was cultivated in three hydroponics systems (i.e., suspended nutrient film technique system, pyramidal aeroponic system, and tower aeroponic system), which interacted with three different magnetic unit strengths under a controlled greenhouse environment during the growing season in 2018 and 2019. Three scenarios consisting of the combinations of input variables (i.e., leaf number, water consumption, dry weight, stem length, and stem diameter) were assessed. The XGB model with scenario 3 (all input variables) yielded the lowest root mean square error (RMSE) of 8.88 g followed by SVR with the same scenario that achieved 9.55 g, and the highest result was by RF with scenario 1 (i.e., leaf number and water consumption) that achieved 12.89 g. All model scenarios having Scatter Index (SI) (i.e., RMSE divided by the average values of the observed yield) values less than 0.1 were classified as excellent in predicting fresh lettuce yield. Based on all of the performance statistics, the two best models were SVR with scenario 3 and DNN with scenario 2 (i.e., leaf number, water consumption, and dry weight). However, DNN with scenario 2 requiring less input variables is preferred. The potential of the DNN model to predict fresh lettuce yield is promising, and it can be applied on a large scale as a rapid tool for decision-makers to manage crop yield.

Mapping 30 m Fractional Forest Cover over China’s Three-North Region from Landsat-8 Data Using Ensemble Machine Learning Methods

The accurate monitoring of forest cover and its changes are essential for environmental change research, but current satellite products for forest coverage carry many uncertainties. This study used 30-m Landsat-8 data, and aggregated 1-m GaoFen-2 (GF-2) satellite images to construct the training samples and used multiple machine learning algorithms (MLAs) to estimate the fractional forest cover (FFC) in China’s Three North Region (TNR). In this study, multiple MLAs were merged to construct stacked generalization (SG) models based on the idea of SG, and the performances of the MLAs in the FFC estimation were evaluated. The results of the 10-fold cross-validation showed that all non-linear algorithms had a good performance, with an R2 value of greater than 0.8 and a root-mean square error (RMSE) of less than 0.05. In the bagging ensemble, the random forest (RF) (R2 = 0.993, RMSE = 0.020) model performed the best and in the boosting ensemble, the light gradient boosted machine (LGBM) (R2 = 0.992, RMSE = 0.022) performed the best. Although the evaluation index of the RF is slightly better than that of the LGBM, the independent validation results show that the two models have similar performances. The model evaluation results of the independent datasets showed that, in the SG model, the performance of the SG(LGBM) (R2 = 0.991, RMSE = 0.034) was better than that of the single or non-ensemble model. Comparing the FFC estimates of our model with those of existing datasets showed that our model exhibited more forest spatial distribution details and higher accuracy in complex landscapes. Overall, in this study, the method of using high-resolution remote sensing (RS) images to extract samples for FFC estimation is feasible. Our results demonstrate the potential of the ensemble MLAs to map the FFC. The research results also show that among many MALs, the RF algorithm is the most suitable algorithm for estimating FFC, which provides a reference for future research.

A Long-Term Spatiotemporal Analysis of Vegetation Greenness over the Himalayan Region Using Google Earth Engine

The Himalayas constitute one of the richest and most diverse ecosystems in the Indian sub-continent. Vegetation greenness driven by climate in the Himalayan region is often overlooked as field-based studies are challenging due to high altitude and complex topography. Although the basic information about vegetation cover and its interactions with different hydroclimatic factors is vital, limited attention has been given to understanding the response of vegetation to different climatic factors. The main aim of the present study is to analyse the relationship between the spatiotemporal variability of vegetation greenness and associated climatic and hydrological drivers within the Upper Khoh River (UKR) Basin of the Himalayas at annual and seasonal scales. We analysed two vegetation indices, namely, normalised difference vegetation index (NDVI) and enhanced vegetation index (EVI) time-series data, for the last 20 years (2001–2020) using Google Earth Engine. We found that both the NDVI and EVI showed increasing trends in the vegetation greening during the period under consideration, with the NDVI being consistently higher than the EVI. The mean NDVI and EVI increased from 0.54 and 0.31 (2001), respectively, to 0.65 and 0.36 (2020). Further, the EVI tends to correlate better with the different hydroclimatic factors in comparison to the NDVI. The EVI is strongly correlated with ET with r2 = 0.73 whereas the NDVI showed satisfactory performance with r2 = 0.45. On the other hand, the relationship between the EVI and precipitation yielded r2 = 0.34, whereas there was no relationship was observed between the NDVI and precipitation. These findings show that there exists a strong correlation between the EVI and hydroclimatic factors, which shows that changes in vegetation phenology can be better captured using the EVI than the NDVI.

The Superiority of Data-Driven Techniques for Estimation of Daily Pan Evaporation

In the present study, estimating pan evaporation (Epan) was evaluated based on different input parameters: maximum and minimum temperatures, relative humidity, wind speed, and bright sunshine hours. The techniques used for estimating Epan were the artificial neural network (ANN), wavelet-based ANN (WANN), radial function-based support vector machine (SVM-RF), linear function-based SVM (SVM-LF), and multi-linear regression (MLR) models. The proposed models were trained and tested in three different scenarios (Scenario 1, Scenario 2, and Scenario 3) utilizing different percentages of data points. Scenario 1 includes 60%: 40%, Scenario 2 includes 70%: 30%, and Scenario 3 includes 80%: 20% accounting for the training and testing dataset, respectively. The various statistical tools such as Pearson’s correlation coefficient (PCC), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and Willmott Index (WI) were used to evaluate the performance of the models. The graphical representation, such as a line diagram, scatter plot, and the Taylor diagram, were also used to evaluate the proposed model’s performance. The model results showed that the SVM-RF model’s performance is superior to other proposed models in all three scenarios. The most accurate values of PCC, RMSE, NSE, and WI were found to be 0.607, 1.349, 0.183, and 0.749, respectively, for the SVM-RF model during Scenario 1 (60%: 40% training: testing) among all scenarios. This showed that with an increase in the sample set for training, the testing data would show a less accurate modeled result. Thus, the evolved models produce comparatively better outcomes and foster decision-making for water managers and planners.

Using the InVEST Model to Assess the Impacts of Climate and Land Use Changes on Water Yield in the Upstream Regions of the Shule River Basin

Water yield is a key ecosystem function index, directly impacting the sustainable development of the basin economy and ecosystem. Climate and land use/land cover (LULC) changes are the main driving factors affecting water yield. In the context of global climate change, assessing the impacts of climate and LULC changes on water yield in the alpine regions of the Qinghai–Tibet Plateau (QTP) is essential for formulating rational management and development strategies for water resources. On the basis of the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model, we simulated and analyzed the spatiotemporal variations and the impacts of LULC and climate changes on water yield from 2001 to 2019 in the upstream regions of the Shule River Basin (USRB) on the northeastern margin of the QTP. Three scenarios were designed in the InVEST model to clearly analyze the contributions of climate and LULC changes on the variation of water yield. The first scenario integrated climate and LULC change into the model according to the actual conditions. The second scenario was simulation without LULC change, and the third scenario was without climate change. The results showed that (1) the InVEST model had a good performance in estimating water yield (coefficient of determination (R2) = 0.986; root mean square error (RMSE) = 3.012, p < 0.05); (2) the water yield significantly increased in the temporal scale from 2001 to 2019, especially in the high altitude of the marginal regions (accounting for 32.01%), while the northwest regions significantly decreased and accounted for only 8.39% (p < 0.05); (3) the spatial distribution of water yield increased from the middle low-altitude regions to the marginal high-altitude regions; and (4) through the analysis of the three scenarios, the impact of climate change on water yield was 90.56%, while that of LULC change was only 9.44%. This study reveals that climate warming has a positive impact on water yield, which will provide valuable references for the integrated assessment and management of water resources in the Shule River Basin.

A high-resolution assessment of climate change impact on water footprints of cereal production in India

Water footprint (WF), a comprehensive indicator of water resources appropriation, has evolved as an efficient tool to improve the management and sustainability of water resources. This study quantifies the blue and green WF of major cereals crops in India using high resolution soil and climatic datasets. A comprehensive modelling framework, consisting of Evapotranspiration based Irrigation Requirement (ETIR) tool, was developed for WF assessment. For assessing climate change impact on WF, multi-model ensemble climate change scenarios were generated using the hybrid-delta ensemble method for RCP4.5 and RCP6.0 and future period of 2030s and 2050s. The total WF of the cereal crops are projected to change in the range of - 3.2 to 6.3% under different RCPs in future periods. Although, the national level green and blue WF is projected to change marginally, distinct trends were observed for Kharif (rainy season-June to September) and rabi (winter season-October to February) crops. The blue WF of paddy is likely to decrease by 9.6%, while for wheat it may increase by 4.4% under RCP4.5 during 2050s. The green WF of rabi crops viz. wheat and maize is likely to increase in the range of 20.0 to 24.1% and 9.9 to 16.2%, respectively. This study provides insights into the influences of climate change on future water footprints of crop production and puts forth regional strategies for future water resource management. In view of future variability in the WFs, a water footprint-based optimization for relocation of crop cultivation areas with the aim of minimising the blue water use would be possible management alternative.

Prediction of Combined Terrestrial Evapotranspiration Index (CTEI) over Large River Basin Based on Machine Learning Approaches

Drought is a fundamental physical feature of the climate pattern worldwide. Over the past few decades, a natural disaster has accelerated its occurrence, which has significantly impacted agricultural systems, economies, environments, water resources, and supplies. Therefore, it is essential to develop new techniques that enable comprehensive determination and observations of droughts over large areas with satisfactory spatial and temporal resolution. This study modeled a new drought index called the Combined Terrestrial Evapotranspiration Index (CTEI), developed in the Ganga river basin. For this, five Machine Learning (ML) techniques, derived from artificial intelligence theories, were applied: the Support Vector Machine (SVM) algorithm, decision trees, Matern 5/2 Gaussian process regression, boosted trees, and bagged trees. These techniques were driven by twelve different models generated from input combinations of satellite data and hydrometeorological parameters. The results indicated that the eighth model performed best and was superior among all the models, with the SVM algorithm resulting in an R2 value of 0.82 and the lowest errors in terms of the Root Mean Squared Error (RMSE) (0.33) and Mean Absolute Error (MAE) (0.20), followed by the Matern 5/2 Gaussian model with an R2 value of 0.75 and RMSE and MAE of 0.39 and 0.21 mm/day, respectively. Moreover, among all the five methods, the SVM and Matern 5/2 Gaussian methods were the best-performing ML algorithms in our study of CTEI predictions for the Ganga basin.