Groundwater is a vital source of freshwater, supporting the livelihood of over two billion people worldwide. The quantitative assessment of groundwater resources is critical for sustainable management of this strained resource, particularly as climate warming, population growth, and socioeconomic development further press the water resources. Rapid growth in the availability of a plethora of in-situ and remotely sensed data alongside advancements in data-driven methods and machine learning offer immense opportunities for an improved assessment of groundwater resources at the local to global levels. This systematic review documents the advancements in this field and evaluates the accuracy of various models, following the protocol developed by the Center for Evidence-Based Conservation. A total of 197 original peer-reviewed articles from 2010–2020 and from 28 countries that employ regression machine learning algorithms for groundwater monitoring or prediction are analyzed and their results are aggregated through a meta-analysis. Our analysis points to the capability of machine learning models to monitor/predict different characteristics of groundwater resources effectively and efficiently. Modeling the groundwater level is the most popular application of machine learning models, and the groundwater level in previous time steps is the most employed input data. The feed-forward artificial neural network is the most employed and accurate model, although the model performance does not exhibit a striking dependence on the model choice, but rather the information content of the input variables. Around 10–12 years of data are required to develop an acceptable machine learning model with a monthly temporal resolution. Finally, advances in machine and deep learning algorithms and computational advancements to merge them with physics-based models offer unprecedented opportunities to employ new information, e.g., InSAR data, for increased spatiotemporal resolution and accuracy of groundwater monitoring and prediction.

Drought is a natural phenomenon that occurs in many places on the planet and may cause considerable damage. Selection of an integrated index for quantifying drought severity is a challenge for decision makers in developing water resources and operation management policies. In this study, the standardized precipitation index, water surface supply index, and Palmer drought severity index have been combined to develop an integrated index, called the hybrid drought index (HDI), using associated damage of drought events. Application of the HDI in drought severity prediction has been examined using two different types of artificial neural networks, namely, a probabilistic neural network and a multilayer perceptron network. These models have been selected due to their special characteristics that are suitable for prediction schemes. The proposed algorithm for developing HDI and drought prediction has been applied to the “Gavkhooni/Zayandeh-rud” basin in the central part of Iran. The results show the merits of ea...

Flood modeling is highly influenced by topography data set. Lower resolution digital elevation models (DEMs) are usually used because of their availability and less computational burden when they are used in modeling applications. However, low accuracy of these DEMs yields to even lower accuracy in flood risk analysis through spatial modeling. This study aims to explore the DEM resolution effects on coastal flood risk assessments. For this purpose, deterministic and probabilistic approaches are employed for flood inundation modeling utilizing hydrologically connected bathtub method. High‐resolution light detection and ranging (LiDAR) DEM is considered as the most accurate data from which different resolution maps are obtained using resampling techniques. This is incorporated into an error analysis framework along with U.S. Geological Survey (USGS) National Elevation Dataset (NED) DEMs. The probabilistic framework is developed by simulating the spatial variability of elevation errors compared to LiDAR DEM through a Monte Carlo‐based method called sequential Gaussian simulation. The proposed methodology is applied to the lower Manhattan in New York City. By integrating the flood model into the developed framework, flood inundation probability at each grid cells is obtained. Furthermore, using the concept of accuracy‐efficiency tradeoffs, a framework for selecting a suitable spatial resolution for probabilistic flood risk assessment has been suggested. The results show that by exercising a range of options presented in this paper, a broader insight into mapping resolution can be provided, improving flood assessment, evacuation zones, and mitigation plans depending upon the data availability in a region.

In this paper, a new Cooperative Trading Discharge Permit (CTDP) methodology is designed for estimating equitable and efficient treatment cost allocation among dischargers in a river system considering their conflicting interests. The methodology consists of two main steps: (1) initial treatment cost allocation and (2) equitable treatment cost reallocation. In the first step, a Pareto front among objectives is developed using a powerful and recently developed multi-objective genetic algorithm known as Nondominated Sorting Genetic Algorithm-II (NSGA-II). The objectives of the optimization model are considered to be the average treatment level of dischargers and a fuzzy risk of violating the water quality standards. The fuzzy risk is evaluated using the Monte Carlo analysis. The best non-dominated solution on the Pareto front, which provides the initial cost allocation to dischargers, is selected using the Young Bargaining Theory (YBT). In the second step, some cooperative game theoretic approaches are utilized to investigate how the maximum saving cost of participating dischargers in a coalition can be fairly allocated to them. The final treatment cost allocation provides the optimal trading discharge permit policies. The practical utility of the proposed methodology for river water quality management is illustrated through a realistic case study of the Zarjub river in the northern part of Iran.