Although estimating the uncertainty of models used for modelling nitrate contamination of groundwater is essential in groundwater management, it has been generally ignored. This issue motivates this research to explore the predictive uncertainty of machine-learning (ML) models in this field of study using two different residuals uncertainty methods: quantile regression (QR) and uncertainty estimation based on local errors and clustering (UNEEC). Prediction-interval coverage

No abstract

This study aims to present an efficient methodology for land use optimization based on minimization of runoff and sediment and maximization of economic benefits, occupational opportunities, and land use suitability in the Tilabad watershed in northeast of Iran. The land use map of the area was prepared using the Landsat satellite images and field surveys. The amounts of runoff and sediment were estimated via SWAT model. The TOPSIS multicriteria decision‐making (MCDM) approach was applied on the results of the multiobjective optimization (MOO) based on non‐dominated sorting genetic algorithm II (NSGA II) to choose the final optimal solution among the Pareto solutions front generated by MOO. The results indicated that the area of agriculture and rangelands should decrease, and the area of forests should increase to achieve the defined objectives. Overall, results indicated that integration of MOO and MCDM provides an efficient procedure for land use optimization in a complex watershed. Recommendations for Resource Managers The optimization of land use allocation across a complex watershed requires the combined application of several models and techniques to achieve a sustainable decision‐making process. By optimization of land use patterns according to the final solution, the surface runoff and sediment load of the watershed will decline, while the economic profit and land use suitability will improve. Despite using a maximization objective function, the land‐based job opportunities might decrease across a watershed by optimization of land use allocation, but this can be considered as an opportunity for provision of manpower to other socioeconomic sectors.

No abstract