Simulation of regional groundwater levels in arid regions using interpretable machine learning models

Enhancing physically-based hydrological modeling with an ensemble of machine-learning reservoir operation modules under heavy human regulation using easily accessible data

Dams and reservoirs have significantly altered river flow dynamics worldwide. Accurately representing reservoir operations in hydrological models is crucial yet challenging. Detailed reservoir operation data is often inaccessible, leading to relying on simplified reservoir operation modules in most hydrological models. To improve the capability of hydrological models to capture flow variability influenced by reservoirs, this study proposes a hybrid hydrological modeling framework, which combines a process-based hydrological model with a machine-learning-based reservoir operation module designed to simulate runoff under reservoir operations. The reservoir operation module employs an ensemble of three machine learning models: random forest, support vector machine, and AutoGluon. These models predict reservoir outflows using precipitation and temperature data as inputs. The Soil and Water Assessment Tool (SWAT) then integrates these outflow predictions to simulate runoff. To evaluate the performance of this hybrid approach, the Xijiang Basin within the Pearl River Basin, China, is used as a case study. The results highlight the superiority of the SWAT model coupled with machine learning-based reservoir operation models compared to alternative modeling approaches. This hybrid model effectively captures peak flows and dry period runoff. The Nash-Sutcliffe Efficiency (NSE) in daily runoff simulations shows substantial improvement, ranging from 0.141 to 0.780, with corresponding enhancements in the coefficient of determination (R2) by 0.098-0.397 when compared to the original reservoir operation modules in SWAT. In comparison to parameterization techniques lacking a dedicated reservoir module, NSE enhancements range from 0.068 to 0.537, and R2 improvements range from 0.027 to 0.139. The proposed hybrid modeling approach effectively characterizes the impact of reservoir operations on river flow dynamics, leading to enhanced accuracy in runoff simulation. These findings offer valuable insights for hydrological forecasting and water resources management in regions influenced by reservoir operations.

Automatedly identify dryland threatened species at large scale by using deep learning

Dryland biodiversity is decreasing at an alarming rate. Advanced intelligent tools are urgently needed to rapidly, automatedly, and precisely detect dryland threatened species on a large scale for biological conservation. Here, we explored the performance of three deep convolutional neural networks (Deeplabv3+, Unet, and Pspnet models) on the intelligent recognition of rare species based on high-resolution (0.3 m) satellite images taken by an unmanned aerial vehicle (UAV). We focused on a threatened species, Populus euphratica, in the Tarim River Basin (China), where there has been a severe population decline in the 1970s and restoration has been carried out since 2000. The testing results showed that Unet outperforms Deeplabv3+ and Pspnet when the training samples are lower, while Deeplabv3+ performs best as the dataset increases. Overall, when training samples are 80, Deeplabv3+ had the best overall performance for Populus euphratica identification, with mean pixel accuracy (MPA) between 87.31 % and 90.2 %, which, on average is 3.74 % and 11.29 % higher than Unet and Pspnet, respectively. Deeplabv3+ can accurately detect the boundaries of Populus euphratica even in areas of dense vegetation, with lower identification uncertainty for each pixel than other models. This study developed a UAV imagery-based identification framework using deep learning with high resolution in large-scale regions. This approach can accurately capture the variation in dryland threatened species, especially those in inaccessible areas, thereby fostering rapid and efficient conservation actions.

Groundwater level forecasting with machine learning models: A review

Groundwater, the world's most abundant source of freshwater, is rapidly depleting in many regions due to a variety of factors. Accurate forecasting of groundwater level (GWL) is essential for effective management of this vital resource, but it remains a complex and challenging task. In recent years, there has been a notable increase in the use of machine learning (ML) techniques to model GWL, with many studies reporting exceptional results. In this paper, we present a comprehensive review of 142 relevant articles indexed by the Web of Science from 2017 to 2023, focusing on key ML models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), evolutionary computing (EC), deep learning (DL), ensemble learning (EN), and hybrid-modeling (HM). We also discussed key modeling concepts such as dataset size, data splitting, input variable selection, forecasting time-step, performance metrics (PM), study zones, and aquifers, highlighting best practices for optimal GWL forecasting with ML. This review provides valuable insights and recommendations for researchers and water management agencies working in the field of groundwater management and hydrology.

Hysteresis response of groundwater depth on the influencing factors using an explainable learning model framework with Shapley values

Machine learning has been widely used for groundwater prediction. However, the hysteresis response of groundwater depth (GD) to input features has not been fully investigated. This study uses an interpretation method to reveal the interplay between climate, human activity, and GD while considering the response of groundwater to multiple factors. Six factors [precipitation (P), wind speed (WS), temperature (T), population (POP), gross domestic product (GDP), and effective irrigated area (EIA)] were selected to analyze the hysteresis response of GD in terms of the lag correlation coefficient and lag time. The correlation between climatic variables and GD was weaker than that of anthropogenic variables. The lag time between variables and different types of GD was less than four months at most sites, except for EIA and WS in deep groundwater. The SVM model achieved satisfactory performance in 89 % of the sites. If there were sharp changes in GD during the testing period or significant variations in its seasonal patterns at different times, the SVM model performed poorly. The model was interpreted using the Shapley additive explanation method. The impact of POP and GDP on deep groundwater in irrigated areas was higher than that of shallow groundwater. In urban areas with intensive human activities, anthropogenic variables were the main factors affecting shallow groundwater while the impact of climate was gradually increasing in the suburbs. The influence of precipitation on shallow groundwater was decreased after water transfer from the South-to-North Water Diversion project. Furthermore, this study proposed a multifactor-driven conceptual model that can provide recommendations for analyzing groundwater dynamics in similar areas.

Predicting risk of obesity in overweight adults using interpretable machine learning algorithms

Objective

To screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.

Methods

This cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.

Results

Machine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.

Conclusion

CatBoost may be the best machine learning method for prediction. Combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Long-run forecasting surface and groundwater dynamics from intermittent observation data: An evaluation for 50 years

The accurate prediction of water dynamics is critical for operational water resource management. In this study, we propose a novel approach to perform long-term forecasts of daily water dynamics, including river levels, river discharges, and groundwater levels, with a lead time of 7-30 days. The approach is based on the state-of-the-art neural network, bidirectional long short-term memory (BiLSTM), to enhance the accuracy and consistency of dynamic predictions. The operation of this forecasting system relies on an in-situ database observed for over 50 years with records gauging in 19 rivers, the karst aquifer, the English Channel, and the meteorological network in Normandy, France. To address the problem of missing measurements and gauge installations over time, we developed an adaptive scheme in which the neural network is regularly adjusted and re-trained in response to changing inputs during a long operation. Advances in BiLSTM with extensive learning past-to-future and future-to-past further help to avoid time-lag calibration that simplifies data processing. The proposed approach provides high accuracy and consistent prediction for the three water dynamics within a similar accuracy range as an on-site observation, with approximately 3 % error in the measurement range for the 7 day-ahead predictions and 6 % error for the 30 d-ahead predictions. The system also effectively fills the gap in actual measurements and detects anomalies at gauges that can last for years. Working with multiple dynamics not only proves that the data-driven model is a unified approach but also reveals the impact of the physical background of the dynamics on the performance of their predictions. Groundwater undergoes a slow filtration process following a low-frequency fluctuation, favoring long-term prediction, which differs from other higher-frequency river dynamics. The physical nature drives the predictive performance even when using a data-driven model.

Incorporating marine particulate carbon into machine learning for accurate estimation of coastal chlorophyll-a

Accurate predictions of coastal ocean chlorophyll-a (Chl-a) concentrations are necessary for dynamic water quality monitoring, with eutrophication as a critical factor. Prior studies that used the driven-data method have typically overlooked the relationship between Chl-a and marine particulate carbon. To address this gap, marine particulate carbon was incorporated into machine learning (ML) and deep learning (DL) models to estimate Chl-a concentrations in the Yang Jiang coastal ocean of China. Incorporating particulate organic carbon (POC) and particulate inorganic carbon (PIC) as predictors can lead to successful Chl-a estimation. The Gaussian process regression (GPR) model significantly outperforming the DL model in terms of stability and robustness. A lower POC/Chl-a ratio was observed in coastal areas, in contrast to the higher ratios detected in the southern regions of the study area. This study highlights the efficacy of the GPR model for estimating Chl-a and the importance of considering POC in modeling Chl-a concentrations.

A wavelet-assisted deep learning approach for simulating groundwater levels affected by low-frequency variability

Groundwater level (GWL) simulations allow the generation of reconstructions for exploring the past temporal variability of groundwater resources or provide the means for generating projections under climate change on decadal scales. In this context, analyzing GWLs affected by low-frequency variations is crucial. In this study, we assess the capabilities of three deep learning (DL) models (long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM)) in simulating three types of GWLs affected by varying low-frequency behavior: inertial (dominated by low-frequency), annual (dominated by annual cyclicity) and mixed (in which both annual and low-frequency variations have high amplitude). We also tested if maximal overlap discrete wavelet transform pre-processing (MODWT) of input variables helps to better identify the frequency content most relevant for the models (MODWT-DL models). Only external variables (i.e., precipitation, air temperature as raw data, and effective precipitation (EP)) were used as input. Results indicate that for inertial-type GWLs, MODWT-DL models with raw data were notably more accurate than standalone models. However, DL models performed well for annual-type GWLs, while using EP as input, with MODWT-DL models exhibiting only minor improvements. Using raw data as input improved MODWT-DL models compared to standalone models; nevertheless, all models using EP performed better for annual-type GWLs. For mixed-type GWLs, while using EP as input, MODWT-DL models performed well, with substantial improvements over standalone models. Using raw data as input, improvement of MODWT-DL models is marginal compared to that of standalone models; nevertheless, they perform better than standalone models with EP. The Shapley Additive exPlanations (SHAP) approach used to interpret models highlighted that they preferentially learned from low-frequency in precipitation data to achieve the best simulations for inertial and mixed GWLs. This study showed that MODWT-based input pre-processing is highly suitable to better simulate low-frequency varying GWLs.

Real-time streamflow forecasting in a reservoir-regulated river basin using explainable machine learning and conceptual reservoir module

Real-time streamflow forecasting is essential to manage water resources effectively in a reservoir-regulated basin. However, forecasting becomes challenging without weather and upstream reservoir outflows forecasts in real-time. In this context, a novel hybrid approach is proposed in this study to forecast the streamflows and reservoir outflows in real-time. In this approach, the Explainable Machine Learning model is embedded with a conceptual reservoir module for forecasting streamflows using short-term weather forecasts. Long Short Term Memory (LSTM), a Machine Learning model, is used in this study to predict the streamflow, and the model's explainability is examined by Shapley additive explanations method (SHAP). Panchet reservoir catchment, which contains Tenughat and Konar reservoirs, is selected as a study area. The LSTM model performance is excellent in predicting the streamflows of Tenughat, Konar and Panchet catchments with NSE values of 0.93, 0.87, and 0.96, respectively. The SHAP method identified the high-impact variables as streamflows and precipitation of 1-day lag. In forecasting, bias-corrected Global Forecast System data is used with the LSTM model to forecast the streamflows in three catchments. The inflows are forecasted well up to a 3-day lead in Tenughat and Konar reservoirs with NSE values above 0.88 and 0.87, respectively. The reservoir module performance in forecasting Tenughat and Konar reservoirs' outflows with the inflow forecasts is also promising up to a 3-day lead with NSE values above 0.88 for both reservoirs. The inflows forecasting to Panchet reservoir with reservoirs' outflows as additional inputs is excellent up to 5-day lead (NSE = 0.96-0.88). However, the forecasting error increased from 77 m³/s to 134 m³/s with the lead time. This approach could provide an efficient way to reduce flood risks in the reservoir-regulated basin.

Mapping of groundwater salinization and modelling using meta-heuristic algorithms for the coastal aquifer of eastern Saudi Arabia

The growing increase in groundwater (GW) salinization in the coastal aquifers has reached an alarming socio-economic menace in Saudi Arabia and various places globally due to several natural and anthropogenic activities. Hence, evaluating the GW salinization is paramount to safeguarding the water resources planning and management. This study presents three different scenarios viz.: real field investigation, experimental laboratory analysis (using ion chromatography (IC) and inductively coupled plasma mass spectrometry (ICP-MS), etc.), and artificial intelligence (AI) based metaheuristic optimization (MO) algorithms in Saudi Arabia. The main purpose of this study is to validate the obtained experimental-based analysis using hybrid MO techniques comprising of adaptive neuro-fuzzy inference system (ANFIS) hybridized with genetic algorithm (GA), particle swarm optimization (PSO), and biogeography-based optimization (BBO) for identification of GW salinization in the coastal region of eastern Saudi Arabia. Additionally, ArcGIS 10.3 software generates the prediction map based on ANFIS-GA, ANFIS-PSO, and ANFIS-BBO. Feature selection was assessed using the PSO algorithm, and four indices evaluated the estimated models, namely, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation (SD). The simulated results are based on three variable input combinations, which showed that the ANFIS-PSO (MAE = 0.00439) algorithm had the highest accuracy (99 %), followed by the ANFIS-GA (MAE = 0.00767) and ANFIS-BBO (MAE = 0.0132) algorithms. Besides, Ca²⁺, Na⁺, Mg²⁺, and Cl^- were the most influential parameters. The accuracy also demonstrated the potential reliability of MO algorithms based on spatial distribution mapping. The employed approach proved to be merit and reliable tool for water resources decision-makers in the coastal aquifer of Saudi Arabia. This approach is believed to improve water scarcity as one of the essential targets for Goal 6 of Sustainable Development Vision 2030 and the Kingdom in general.

A Novel Groundwater Burial Depth Prediction Model Based on Two-Stage Modal Decomposition and Deep Learning

The variability of groundwater burial depths is critical to regional water management. In order to reduce the impact of high-frequency eigenmodal functions (IMF) generated by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) on the prediction results, variational modal decomposition (VMD) is performed on the high frequency IMF components after the primary modal decomposition. A convolutional neural network-gated recurrent unit prediction model (CNN-GRU) is proposed to address the shortcomings of traditional machine learning which cannot handle correlation information and temporal correlation between time series. The CNN-GRU model can extract the implicit features of the coupling relationship between groundwater burial depth and time series and further predict the groundwater burial depth time series. By comparing the prediction results with GRU, CEEMDAN-GRU, and CEEMDAN-CNN-GRU models, we found that the CEEMDAN-VMD-CNN-GRU prediction model outperformed the other prediction models, with a prediction accuracy of 94.29%, good prediction results, and high model confidence.

Mathematical and Machine Learning Models for Groundwater Level Changes: A Systematic Review and Bibliographic Analysis

With the effects of climate change such as increasing heat, higher rainfall, and more recurrent extreme weather events including storms and floods, a unique approach to studying the effects of climatic elements on groundwater level variations is required. These unique approaches will help people make better decisions. Researchers and stakeholders can attain these goals if they become familiar with current machine learning and mathematical model approaches to predicting groundwater level changes. However, descriptions of machine learning and mathematical model approaches for forecasting groundwater level changes are lacking. This study picked 117 papers from the Scopus scholarly database to address this knowledge gap. In a systematic review, the publications were examined using quantitative and qualitative approaches, and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) was chosen as the reporting format. Machine learning and mathematical model techniques have made significant contributions to predicting groundwater level changes, according to the study. However, the domain is skewed because machine learning has been more popular in recent years, with random forest (RF) methods dominating, followed by the methods of support vector machine (SVM) and artificial neural network (ANN). Machine learning ensembles have also been found to help with aspects of computational complexity, such as performance and training times. Furthermore, compared to mathematical model techniques, machine learning approaches achieve higher accuracies, according to our research. As a result, it is advised that academics employ new machine learning techniques while also considering mathematical model approaches to predicting groundwater level changes.