|
|
Singh, A., Patel, S., Bhadani, V., Kumar, V., & Gaurav, K. (2024). AutoML-GWL: Automated machine learning model for the prediction of groundwater level. Engineering Applications of Artificial Intelligence, 127, 107405.
Abstract: Predicting groundwater levels is pivotal in curbing overexploitation and ensuring effective water resource governance. However, groundwater level prediction is intricate, driven by dynamic nonlinear factors. To comprehend the dynamic interaction among these drivers, leveraging machine learning models can provide valuable insights. The drastic increase in computational capabilities has catalysed a substantial surge in the utilisation of machine learning-based solutions for effective groundwater management. The performance of these models highly depends on the selection of hyperparameters. The optimisation of hyperparameters is a complex process that often requires application-specific expertise for a skillful prediction. To mitigate the challenge posed by hyperparameter tuning’s problem-specific nature, we present an innovative approach by introducing the automated machine learning (AutoML-GWL) framework. This framework is specifically designed for precise groundwater level mapping. It seamlessly integrates the selection of best machine learning model and adeptly fine-tunes its hyperparameters by using Bayesian optimisation. We used long time series (1997-2018) data of precipitation, temperature, evaporation, soil type, relative humidity, and lag of groundwater level as input features to train the AutoML-GWL model while considering the influence of Land Use Land Cover (LULC) as a contextual factor. Among these input features, the lag of groundwater level emerged as the most relevant input feature. Once the model is trained, it performs well over the unseen data with a strong correlation of coefficient (R = 0.90), low root mean square error (RMSE = 1.22), and minimal bias = 0.23. Further, we compared the performance of the proposed AutoML-GWL with sixteen benchmark algorithms comprising baseline and novel algorithms. The AutoML-GWL outperforms all the benchmark algorithms. Furthermore, the proposed algorithm ranked first in Friedman’s statistical test, confirming its reliability. Moreover, we conducted a spatial distribution and uncertainty analysis for the proposed algorithm. The outcomes of this analysis affirmed that the AutoML-GWL can effectively manage data with spatial variations and demonstrates remarkable stability when faced with small uncertainties in the input parameters. This study holds significant promise in revolutionising groundwater management practices by establishing an automated framework for simulating groundwater levels for sustainable water resource management.
|
|
|
|
Stavi, I., Eldad, S., Xu, C., Xu, Z., Gusarov, Y., Haiman, M., et al. (2024). Ancient agricultural terrace walls control floods and regulate the distribution of Asphodelus ramosus geophytes in the Israeli arid Negev. Catena, 234, 107588.
Abstract: Ancient stone terrace walls aimed at harvesting water runoff and facilitating crop production are widespread across the drylands of the Middle East and beyond. In addition to retaining the scarce water resource, the terrace walls also conserve soil and thicken its profile along ephemeral stream channels (wadis) by decreasing fluvial connectivity and mitigating erosional processes. In this study, we created hydrological models for three wadis with ancient stone terrace walls in the arid northern Negev of Israel, where the predominant geophyte species is Asphodelus ramosus L. A two-dimensional (2D) rain-on-grid (RoG) approach with a resolution of 2 m was used to simulate the rain events with return periods of 10, 20, 50, and 99 % (10-y, 5-y, 2-y, and yearly, respectively) based on the Intensity-Duration-Frequency rain curves for the region. To evaluate the effect of stone terrace walls on fluvial hydrology and geomorphology, the ground level was artificially elevated by 20 cm at the wall locations in a digital terrain model (DTM), using the built-in HEC-RAS 2D terrain modification tool. Our results showed that the terraced wadis have a high capacity to mitigate runoff loss, but a lesser capacity to delay the peak flow. Yet, for all rainstorm return periods, peak flow mitigation was positively related to the number of terrace walls along the stream channel. Field surveys in two of the studied wadis demonstrated that the A. ramosus clones were found in proximity to the stone terrace walls, presumably due to the greater soil–water content there. The results thus suggest that the terrace walls provide improved habitat conditions for these geophytes, supporting their growth and regulating their distribution along the wadi beds.
|
|
