Gully erosion mapping susceptibility in a Mediterranean environment: A hybrid decision-making model

Gully erosion is one of the main natural hazards,especially in arid and semi-arid regions,destroying ecosystem service and human well-being.Thus,gully erosion susceptibility maps(GESM)are urgently needed for identifying priority areas on which appropriate measurements should be considered.Here,we proposed four new hybrid Machine learning models,namely weight of evidence-Multilayer Perceptron(MLP-WoE),weight of evidence–K Nearest neighbours(KNN-WoE),weight of evidence-Logistic regression(LR-WoE),and weight of evidence-Random Forest(RF-WoE),for mapping gully erosion exploring the opportunities of GIS tools and Remote sensing techniques in the El Ouaar watershed located in the Souss plain in Morocco.Inputs of the developed models are composed of the dependent(i.e.,gully erosion points)and a set of independent variables.In this study,a total of 314 gully erosion points were randomly split into 70%for the training stage(220 gullies)and 30%for the validation stage(94 gullies)sets were identified in the study area.12 conditioning variables including elevation,slope,plane curvature,rainfall,distance to road,distance to stream,distance to fault,TWI,lithology,NDVI,and LU/LC were used based on their importance for gully erosion susceptibility mapping.We evaluate the performance of the above models based on the following statistical metrics:Accuracy,precision,and Area under curve(AUC)values of receiver operating characteristics(ROC).The results indicate the RF-WoE model showed good accuracy with(AUC=0.8),followed by KNN-WoE(AUC=0.796),then MLP-WoE(AUC=0.729)and LR-WoE(AUC=0.655),respectively.Gully erosion susceptibility maps provide information and valuable tool for decision-makers and planners to identify areas where urgent and appropriate interventions should be applied.

Integrated Multi-Head Self-Attention Transformer model for electricity demand prediction incorporating local climate variables

This paper develops a trustworthy deep learning model that considers electricity demand(G)and local climate conditions.The model utilises Multi-Head Self-Attention Transformer(TNET)to capture critical information from𝐻,to attain reliable predictions with local climate(rainfall,radiation,humidity,evaporation,and maximum and minimum temperatures)data from Energex substations in Queensland,Australia.The TNET model is then evaluated with deep learning models(Long-Short Term Memory LSTM,Bidirectional LSTM BILSTM,Gated Recurrent Unit GRU,Convolutional Neural Networks CNN,and Deep Neural Network DNN)based on robust model assessment metrics.The Kernel Density Estimation method is used to generate the prediction interval(PI)of electricity demand forecasts and derive probability metrics and results to show the developed TNET model is accurate for all the substations.The study concludes that the proposed TNET model is a reliable electricity demand predictive tool that has high accuracy and low predictive errors and could be employed as a stratagem by demand modellers and energy policy-makers who wish to incorporate climatic factors into electricity demand patterns and develop national energy market insights and analysis systems.