An investigation into time-variant subsidence potentials using inclusive multiple modelling strategies

Scrutinization of land subsidence rate using a supportive predictive model: Incorporating radar interferometry and ensemble soft-computing

Land subsidence is a huge challenge that land and water resource managers are still facing. Radar datasets revolutionize the way and give us the ability to provide information about it, thanks to their low cost. But identifying the most important drivers need for the modeling process. Machine learning methods are especially top of mind amid the prediction studies of natural hazards and hit new heights over the last couple of years. Hence, putting an efficient approach like integrated radar-and-ensemble-based method into practice for land subsidence rate simulation is not available yet which is the main aim of this research. In this study, the number of 52 pairs of radar images were used to identify subsidence from 2014 to 2019. Then, using the simulated annealing (SA) algorithm the key variables affecting land subsidence were identified among the topographical parameters, aquifer information, land use, hydroclimatic variables, and geological and soil factors. Afterward, three individual machine learning models (including Support Vector Machine, SVM; Gaussian Process, GP; Bayesian Additive Regression Tree, BART) along with three ensemble learning approaches were considered for land subsidence rate modeling. The results indicated that the subsidence varies between 0 and 59 cm in this period. Comparing the Radar results with the permanent geodynamic station exhibited a very strong correlation between the ground station and the radar images (R2 = 0.99, RMSE = 0.008). Parsing the input data by the SA indicated that key drivers are precipitation, elevation, percentage of fine-grained materials in the saturated zone, groundwater withdrawal, distance to road, groundwater decline, and aquifer thickness. The performance comparison indicated that ensemble models perform better than individual models, and among ensemble models, the nonlinear ensemble approach (i.e., BART model combination) provided better performance (RMSE = 0.061, RSR = 0.42, R2 = 0.83, PBIAS = 2.2). Also, the distribution shape of the probability density function in the non-linear ensemble model is much closer to the observations. Results indicated that the presence of significant fine-grained materials in unconsolidated aquifer systems can clarify the response of the aquifer system to groundwater decline, low recharge, and subsequent land subsidence. Therefore, the interaction between these factors can be very dangerous and intensify subsidence.

Quantifying the groundwater total contamination risk using an inclusive multi-level modelling strategy

This paper investigates aggregated risks in aquifers, where risk exposures may originate from different contaminants e.g. nitrate-N (NO₃-N), arsenic (As), boron (B), fluoride (F), and aluminium (Al). The main goal is to develop a new concept for the total risk problem under sparse data as an efficient planning tool for management through the following methodology: (i) mapping aquifer vulnerability by DRASTIC and SPECTR frameworks; (ii) mapping risk indices to anthropogenic and geogenic contaminants by unsupervised methods; (iii) improving the anthropogenic and geogenic risks by a multi-level modelling strategy at three levels: Level 1 includes Artificial Neural Networks (ANN) and Support Vector Machines (SVM) models, Level 2 combines the outputs of Level 1 by unsupervised Entropy Model Averaging (EMA), and Level 3 integrates the risk maps of various contaminants (nitrate-N, arsenic, boron, fluoride, and aluminium) modelled at Level 2. The methodology offers new data layers to transform vulnerability indices into risk indices and thereby integrates risks by a heuristic scheme but without any learning as no measured values are available for the integrated risk. The results reveal that the risk indexing methodology is fit-for-purpose. According to the integrated risk map, there are hotspots at the study area and exposed to a number of contaminants (nitrate-N, arsenic, boron, fluoride, and aluminium).

Rainfall prediction using multiple inclusive models and large climate indices

Rainfall prediction is vital for the management of available water resources. Accordingly, this study used large lagged climate indices to predict rainfall in Iran's Sefidrood basin. A radial basis function neural network (RBFNN) and a multilayer perceptron (MLP) network were used to predict monthly rainfall. The models were trained using the naked mole rat (NMR) algorithm, firefly algorithm (FFA), genetic algorithm (GA), and particle swarm optimization (PSO) algorithm. Large lagged climate indices, as well as three hybrid models, i.e., inclusive multiple model (IMM)-MLP, IMM-RBFNN, and the simple average method (SAM), were then employed to predict rainfall. This paper aims to predict rainfall using large climate indices, ensemble models, and optimized artificial neural network models. Also, the paper considers the uncertainty resources in the modeling process. The inputs were selected using a new input selection method, namely a hybrid gamma test (GT). The GT was integrated with the NMR algorithm to create a new test for determining the best input scenario. Therefore, the main innovations of this study were the introduction of the new ensemble and the new hybrid GT, as well as the new MLP and RBFNN models. The introduced ensemble models of the current study are not only useful for rainfall prediction but also can be used to predict other metrological parameters. The uncertainty of the model parameters and input data were also analysed. It was found that the IMM-MLP model reduced the root mean square error (RMSE) of the IMM-RBFNN, SAM, MLP-NMR, RBFNN-NMR, MLP-FFA, RBFNN-FFA, MLP-PSO, RBFNN-PSO, MLP-GA, and RBFNN-GA, MLP, and RBFNN models by 12%, 25%, 31%, 55%, 60%, 62%, 66%, 69%, 70%, 71%, 72%, and 72%, respectively. The IMMs, such as the IMM-MLP, IMM-RBFNN, and SAM, outperformed standalone models. The uncertainty bound of the multiple inclusive models was narrower than that of the standalone MLP and RBFNN models. The MLP-NMR model decreased the RMSE of the RBFNN-NMR, RBFNN-FFA, RBFNN-PSO, and RBFNN models by 15%, 26%, 37%, 42%, and 45%, respectively. The proposed ensemble models were robust tools for combining standalone models to predict hydrological variables.

Investigating meteorological/groundwater droughts by copula to study anthropogenic impacts

A critical understanding of the water crisis of Lake Urmia is the driver in this paper for a basin-wide investigation of its Meteorological (Met) droughts and Groundwater (GW) droughts. The challenge is to formulate a data-driven modelling strategy capable of discerning anthropogenic impacts and resilience patterns through using 21-years of monthly data records. The strategy includes: (i) transforming recorded timeseries into Met/GW indices; (ii) extracting their drought duration and severity; and (iii) deriving return periods of the maximum drought event through the copula method. The novelty of our strategy emerges from deriving return periods for Met and GW droughts and discerning anthropogenic impacts on GW droughts. The results comprise return periods for Met/GW droughts and their basin-wide spatial distributions, which are delineated into four zones. The information content of the results is statistically significant; and our interpretations hint at the basin resilience is already undermined, as evidenced by (i) subsidence problems and (ii) altering aquifers' interconnectivity with watercourses. These underpin the need for a planning system yet to emerge for mitigating impacts and rectifying their undue damages. The results discern that aquifer depletions stem from mismanagement but not from Met droughts. Already, migration from the basin area is detectable.

Land subsidence susceptibility mapping using PWRSTFAL framework and analytic hierarchy process: fuzzy method (case study: Damaneh-Daran Plain in the west of Isfahan Province, Iran)

Land subsidence susceptibility mapping is a necessary prerequisite for land subsidence management. Proper assessment of land subsidence requires determining parameters affecting subsidence to discover the spatial relationships with subsidence. For this purpose, two frameworks were prepared, according to the land site subsidence, eight parameters affecting the subsidence in the Damaneh-Daran plain. In the first framework, eight parameters including annual groundwater level drawdown, aquifer medium, land use, discharge, aquifer saturation thickness, net recharge, fault proximity and topography called PWRSTFAL based on weighting parameters and the second model based on optimization and compatibility of eight active layers on subsidence, were prepared by AHP-fuzzy method and the final map of subsidence vulnerability obtained. Radar images and the InSAR method validated the methods. The results show that both maps show a good correlation with radar data. Still, the map prepared by the AHP-fuzzy method offers the highest correlation with radar data and subsidence in the plain. It separates subsidence vulnerability in more detail on the whole surface of the plain. According to this model, most plain areas, especially the eastern part, are subject to subsidence, and management programs should control subsidence. The results ROC diagram obtained from the performance of the PWRSTFAL framework based on the AHP-fuzzy method was more promising than the ordinary PWRSTFAL framework.

A study of uncertainties in groundwater vulnerability modelling using Bayesian model averaging (BMA)

Bayesian Model Averaging (BMA) is used to study inherent uncertainties using the Basic DRASTIC Framework (BDF) for assessing the groundwater vulnerability in a study area related to Lake Urmia. BMA is naturally an Inclusive Multiple Modelling (IMM) strategy at two levels; at Level 1 multiple models are constructed and the paper constructs three AI (Artificial Intelligence) models, which comprise ANN (Artificial Neural Network), GEP (Gene Expression Programming), and SVM (Support Vector Machines) but their outputs are fed to the next level model; at Level 2, BMA combines ANN, GEP and SVM (the Level 1 models) to quantify their inherent uncertainty in terms of within and in-between model errors. The model performance is tested by using the nitrate-N concentrations measured for the aquifer. The results show that in this particular study area, Level 1 models, even BDF, are quite accurate, but the above modelling strategy maximises the extracted information from the local data and BMA reveals that the higher uncertainties occur at areas with higher vulnerability; whereas lower uncertainties are observed at areas with lower vulnerabilities.

Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques

Groundwater over-abstraction may cause land subsidence (LS), and the LS mapping suffers the subjectivity associated with expert judgment. The paper seeks to reduce the subjectivity associated with the hazard, vulnerability, and risk mapping by formulating an inclusive multiple modeling (IMM), which combines two common approaches of multi-criteria decision-making (MCDM) at Level 1 and artificial intelligence (AI) at Level 2. Fuzzy catastrophe scheme (FCS) is used as MCDM, and support vector machine (SVM) is employed as AI. The developed methodology is applied in Iran’s Tasuj plain, which has experienced groundwater depletion. The result highlights hotspots within the study area in terms of hazard, vulnerability, and risk. According to the receiver operating characteristic and the area under curve (AUC), significant signals are identified at both levels; however, IMM increases the modeling performance from Level 1 to Level 2, as a result of its multiple modeling capabilities. In addition, the AUC values indicate that LS in the study area is caused by intrinsic vulnerability rather than man-made hazards. Still, the hazard plays the triggering role in the risk realization.