Search

This study investigates the increasing severity and recurrence of droughts in Saudi Arabia, focusing on the spatiotemporal dynamics of vegetation stress. Using Earth Observation (EO) data from 2004 to 2021, the research employs advanced statistical methods and remote sensing indices—Standardized Precipitation Evapotranspiration Index (SPEI), Temperature Condition Index (TCI), and Vegetation Condition Index (VCI)—to compute the Vegetation Health Index (VHI) for drought monitoring. The analysis integrates pixel-scale trend assessments, Mann-Kendall test, and Sen’s slope estimator to detect significant changes in drought conditions. Additionally, Wavelet Transformation was applied to explore drought periodicity, revealing cyclical drought patterns. The results highlight substantial climatic variability, with extreme droughts increasing, particularly between 2014 and 2018. Spatial trend analysis shows vegetation in southern and central Saudi Arabia has experienced persistent stress due to recurrent drought and rising temperatures. The study underscores the importance of climate-driven water management and adaptive strategies in mitigating drought impacts. By providing comprehensive insights into drought cycles and vegetation responses, this research contributes valuable knowledge for policymakers to enhance agricultural resilience and resource sustainability in arid regions. [ABSTRACT FROM AUTHOR]

The study aims to create a novel artificial intelligence model-based landslide susceptibility model (LSM) at Aqabat, Saudi Arabia. For LSM, a combination of bagging, dagging, random forest (RF) ensemble with locally weighted learning (LWL), viz. bagging- LWL, dagging-LWL, and RF-LWL has been developed. The 50 landslide areas were divided into two categories training (40) and testing (10). For training datasets, the LWL-Bagging model had the highest AUC value of ROC curve (AUC-0.91), followed by LWL-RF (AUC-0.881), LWL-Dagging (AUC-0.88) and LWL (AUC-0.875). For testing datasets, AUC values of ROC curve of 0.891, 0.876, 0.868, and 0.844 were found for LWL-Bagging, LWL-RF, LWL-Dagging, and LWL, respectively. Based on AUC value, all hybrid machines learning models performed well, but LWL-Bagging model performed as the best fit model. The potential ecosystem loss services were assessed by assessing possible landslide hazards. The research delivers reliable results to influence policy decisions on ecosystem management and landslide-assessment. [ABSTRACT FROM AUTHOR]

Landslides and other catastrophic environmental disasters pose a significant danger to environmental, infrastructure, and people's lives. This research aimed to construct four optimized ensemble machine learning algorithms for landslide susceptibility (LS) mapping, namely particle swarm optimization (PSO) based artificial neural network (ANN), random forest, M5P, and support vector machine. The logistic regression (LR) model was then applied to the four-ensemble machine learning model and generated a hybrid optimized machine learning model. The receiver operating characteristics (ROC) curve was then used to validate LS map. The best model of four LS models depending on ROC's area under curve (AUC) is PSO-ANN (AUC-0.958) model. Also, LR model-based hybrid ensemble machine learning model achieved better accuracy (AUC: 0.962) than PSO-ANN model. Various resources, viz. grassland, built-up, and scarce foliage, are declared as landslide risk zones. Finally, elevation, soil-texture, slope, rainfall, and road distance are considered the most sensitive parameters for landslide occurrences. [ABSTRACT FROM AUTHOR]

The present study uses Landsat satellite images of 1990, 2000 and 2018 to identify the land-use changes. Multilayer perceptron-neural network based land change modelling (LCM) has been applied to model future land-use/land cover (LULC). The prediction model has been validated using simulated and classified LULC maps of 2018 which resulted into an overall accuracy of 88%. The results indicate 389.27% increase in built-up area as the prominent land-use change during 1990–2018 and an increase of 56.25% in built-up area is forecasted during the year 2018–2040. Land absorption coefficient and land consumption rate indices, used to characterize urban expansion, indicate continued compact built-up structure during 1990–2018 due to population increase. The observations derived from this study would be useful as it will help the regional planners with forecasted land-use beforehand in planning the built-up and abundantly available natural resources in the area according to the increasing future demands. [ABSTRACT FROM AUTHOR]

Soil erosion poses a significant threat to sustainable land management and agricultural productivity. Addressing this issue requires advanced predictive models that can accurately identify areas at risk and inform soil conservation strategies. This study focuses on the development and interpretation of well-optimized deep learning (DL) models to predict soil erosion probability, aiming to enhance decision-making in land management. Utilizing the Revised Universal Soil Loss Equation (RUSLE) in conjunction with ground-truthing, we identified critical erosion-prone areas. To predict soil erosion probability, we employed Bayesian optimization to fine-tune Deep Neural Network (DNN), Convolutional Neural Network (CNN), Fully Connected Neural Network (FCNN), and DNN-CNN hybrid models. These DL models were verified using a set of metrics. SHAP value analysis as a means of explainable artificial intelligence (XAI) was used to interpret these DL models for better decision-making. RUSLE estimations and ground truthing highlight that Soil erosion rates in the northeastern and northwestern regions are nearing the highest observed at 25 tonnes per hectare annually, largely due to steep slopes and limited vegetation. In contrast, the southern and southeastern areas have lower erosion rates, due to denser vegetation and gentler slopes. Deep learning models, optimized using Bayesian methods, demonstrate high performance in spatially modeling soil erosion probability. The DNN model achieved an accuracy of 0.93, a precision of 0.92, and an F1-score of 0.94, identifying 222.73 sq. km as highly susceptible to erosion, which indicates its strong ability to detect true erosion events. The CNN model identified 49.68% of the study area (503.30 sq. km) as high-risk, with an accuracy of 0.90 and a precision of 0.91. The FCNN model showed a balanced risk distribution, indicating 37.04% of the land (375.25 sq. km) as very low risk and 36.43% (369.11 sq. km) as very high risk, with an accuracy of 0.91. The DNN-CNN hybrid model highlighted 41.58% of the area (421.20 sq. km) as high risk, demonstrating its effectiveness in capturing spatial patterns of erosion susceptibility. SHAP value analysis indicates that land use and soil type (LULC and K-factor) are crucial in erosion predictions, with LULC having a significant predictive influence in the DNN model. These insights facilitate the prioritization of soil conservation measures, enabling decision-makers to focus on the most impactful factors for mitigating soil erosion. [ABSTRACT FROM AUTHOR]

The present paper proposes a novel fuzzy-VORS (vigor, organization, resilience, ecosystem services) model by integrating fuzzy logic and a VORS model to predict ecosystem health conditions in Abha city of Saudi Arabia from the past to the future. In this study, a support vector machine (SVM) classifier was utilized to classify the land use land cover (LULC) maps for 1990, 2000, and 2018. The LULCs dynamics in 1990–2000, 2000–2018, and 1990–2018 were computed using delta (Δ) change and Markovian transitional probability matrix. The future LULC map for 2028 was predicted using the artificial neural network-cellular automata model (ANN-CA). The machine learning algorithms, such as random forest (RF), classification and regression tree (CART), and probability distribution function (PDF) were utilized to perform sensitivity analysis. Pearson's correlation technique was used to explore the correlation between the predicted models and their driving variables. The ecosystem health conditions for 1990–2028 were predicted by integrating the fuzzy inference system with the VORS model. The results of LULC maps showed that urban areas increased by 334.4% between 1990 and 2018. Except for dense vegetation, all the natural resources and generated ecosystem services have been decreased significantly due to the rapid and continuous urbanization process. A future LULC map (2028) showed that the built-up area would be 343.72 km2. The new urban area in 2028 would be 169 km2. All techniques for sensitivity analysis showed that proximity to urban areas, vegetation, and scrubland are highly sensitive to land suitability models to simulate and predict LULC maps of 2018 and 2028. Global sensitivity analysis showed that fragmentation or organization was the most sensitive parameter for ecosystem health conditions. [ABSTRACT FROM AUTHOR]

Land surface temperature is a significant source of energy budget and climate information, contributing to various environmental and biophysical processes. This research includes comparing the LSTs retrieved from the ASTER sensor using the Reference Channel method, the Emissivity Normalization method (NOR), TES method and Retrieving LSE by taking the proportion of vegetation cover coupled with NDVI and integrates it into the TES algorithm. The results of derived LST from the four algorithms compare with MODIS data of 7 control points having thermally homogenous sites. The analysis showed that the four algorithms are suitable for LST retrieval, whereby the proposed emissivity-derived NDVI algorithms exhibited the highest degree of accuracy (RMSE 0.145), and the NOR had the least accuracy (RMSE 0.403). The analysis shows that emissivity derived NDVI TES method more reliant on the upwelling, downwelling and transmittance and will achieve the best results compared to the other three algorithms. [ABSTRACT FROM AUTHOR]

Accurate soil organic matter (SOM) estimation could provide critical information to understand soil organic carbon sequestration, soil fertility, and the global carbon cycle. A nearest-neighbourhood autoregressive moving average (NN-ARMA) modelling technique along with linear regression has been used to predict localized soil SOM variation based on topographical characteristics and vegetation indices in semi-arid region of Saudi Arabia. Seven topographic variables derived using DEM, and twelve vegetation indices obtained from Landsat 8 used in the model. The best NN-ARMA model showed seven significant variables explaining 96.4% of the total variation of SOM, whereas the best linear regression model could explain 78.8% of the total variation of SOM. The results showed that NN-ARMA model gave better results compared to the linear regression model. Our research gave a better understanding of the possibility of accurate estimation of SOM using the NN-ARMA approach using topographical characteristics and vegetation indices easily acquired by RS sensors. [ABSTRACT FROM AUTHOR]

Accurate and in-time prediction of crop yield plays a crucial role in the planning, management, and decision-making processes within the agricultural sector. In this investigation, utilizing area under irrigation (%) as an exogenous variable, we have made an exertion to assess the suitability of different hybrid models such as ARIMAX (Autoregressive Integrated Moving Average with eXogenous Regressor)–TDNN (Time-Delay Neural Network), ARIMAX–NLSVR (Non-Linear Support Vector Regression), ARIMAX–WNN (Wavelet Neural Network), ARIMAX–CNN (Convolutional Neural Network), ARIMAX–RNN (Recurrent Neural Network) and ARIMAX–LSTM (Long Short Term Memory) as compared to their individual counterparts for yield forecasting of major Rabi crops in India. The accuracy of the ARIMA model has also been considered as a benchmark. Empirical outcomes reveal that the ARIMAX–LSTM hybrid modeling combination outperforms all other time series models in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE) values. For these models, an average improvement of RMSE and MAPE values has been observed to be 10.41% and 12.28%, respectively over all other competing models and 15.83% and 18.42%, respectively over the benchmark ARIMA model. The incorporation of the area under irrigation (%) as an exogenous variable in the ARIMAX framework and the inbuilt capability of the LSTM model to process complex non-linear patterns have been observed to significantly enhance the accuracy of forecasting. The performance supremacy of other hybrid models over their individual counterparts has also been evident. The results also suggest avoiding any performance generalization of individual models for their hybrid structures. [ABSTRACT FROM AUTHOR]

The study develops the displacement error recovery method in a mesh free environment for the finite element solution employing the radial point interpolation (RPI) technique. The RPI technique uses the radial basis functions (RBF), along with polynomials basis functions to interpolate the displacement fields in a node patch and recovers the error in displacement field. The global and local errors are quantified in both energy and L2 norms from the post-processed displacement field. The RPI technique considers multi-quadrics/gaussian/thin plate splint RBF in combination with linear basis function for displacement error recovery analysis. The elastic plate examples are analyzed to demonstrate the error convergence and effectivity of the RPI displacement recovery procedures employing mesh free and mesh dependent patches. The performance of a RPI-based error estimators is also compared with the mesh dependent least square based error estimator. The triangular and quadrilateral elements are used for the discretization of plates domains. It is verified that RBF with their shape parameters, choice of elements, and errors norms influence considerably on the RPI-based displacement error recovery of finite element solution. The numerical results show that the mesh free RPI-based displacement recovery technique is more effective and achieve target accuracy in adaptive analysis with the smaller number of elements as compared to mesh dependent RPI and mesh dependent least square. It is also concluded that proposed mesh free recovery technique may prove to be most suitable for error recovery and adaptive analysis of problems dealing with large domain changes and domain discontinuities. [ABSTRACT FROM AUTHOR]

Changes in precipitation as a result of climate change are becoming a widespread issue all around the world. A lack of rainfall causes a meteorological drought. The short-term Standardized Precipitation Index (SPI-6) index was used to estimate meteorological drought conditions in Saudi Arabia's Asir region from 1970 to 2017. Innovative trend analysis (ITA), the Modified Mann–Kendall test (MMK), the Sequential Mann–Kendall test, and Morlet wavelet transformation were used to detect trend and periodicity in meteorological drought conditions in the Asir region. In addition, the meteorological drought conditions were forecasted by integrating Particle Swarm Optimization (PSO) ensemble machine learning algorithm and an artificial neural network (ANN). Droughts of varying severity have become more frequent in Asir, according to the findings. In most stations, ITA and MMK tests have revealed a significant increase in drought. In all stations, the SQMK test revealed a big sudden year-over-year drought trend. With the exception of one station, all stations experienced extreme drought frequency discovered using Morlet Wavelet Transformation over a long period of time (10 years or more) (station 34). The PSO-ANN hybrid learning algorithm predicted SPI-6 values that had a strong correlation with actual SPI-6 values and also had lower error values, indicating that this model performed well. The PSO-ANN model predicts that the Asir region of Saudi Arabia will experience major moderate to extreme drought events in the coming years (2018–2025). The findings of this analysis will assist planners and policymakers in planning for the acquisition of sustainable agriculture in the study area. [ABSTRACT FROM AUTHOR]

MERS-CoV first case was reported on 23rd November 2012 in Saudi Arabia, Since, then MERS has remained on World Health Organization (WHO) Blueprint list and declared pandemic. This study was conducted on MERS lab confirmed cases reported to Ministry of Health, Saudi Arabia and WHO for year 2012–2019. The epidemiology was investigated based on infection rate, death rate, case fatality rate, Gender, Age group, and Medical conditions (Comorbid and Symptomatic). The overall median age of infected male was 58 years and of female was 45 years. While average mortality age in male was 60 years and of female was 65 years which is greater than the global average of 50 years. The results also report that specially after age of 40 years in both men and women, chances of infection are more while comorbidities increase the infection rate. The men are more susceptible to infection than women. In case of asymptomatic distribution trend was vice versa with 69.4% women and 30.6% in men. Second, most infected age group was reduced by 20 years in case of men with 47.37% infection for age group of 20–39 years. This was also observed in age-group of 20–39 years for no comorbid cases (men (50%) & women (79%)). This explains MERS-CoV prevalence in Saudi Arabia, as young and healthy population were infected, and acted as carrier and on coming in contact with vulnerable population (Elderly, chronic and comorbid) transferred the infection. Hence, MERS-CoV outbreak kept on happening from time to time over past years. This finding might very well explain the exponential spread of Novel CoV-19 globally, as initial control measures required older people to stay indoors while younger generation brought infection from outside. Further studies are required for epidemiology analysis based on clusters, travel history and specific disease related mortality. Unlabelled Image • In overall MERS-CoV distribution most infected age group was 50–59 years. • Male (%) > Female (%) in rate of infection, mortality and fatality. • Female (69.35%) infection was > than male (40.65%) for Asymptomatic cases. • In no comorbid and asymptomatic cases highest infected age group was 20–39 years. [ABSTRACT FROM AUTHOR]