Determination of flood probability and prioritization of sub-watersheds: A comparison of game theory to machine learning

Application of classification machine learning algorithms for characterizing nutrient transport in a clay plain agricultural watershed

Excess nutrients in surface water and groundwater can lead to water quality deterioration in available water resources. Thus, the classification of nutrient concentrations in water resources has gained significant attention during recent decades. Machine learning (ML) algorithms are considered an efficient tool to describe nutrient loss from agricultural land to surface water and groundwater. Previous studies have applied regression and classification ML algorithms to predict nutrient concentrations in surface water and/or groundwater, or to categorize an output variable using a limited number of input variables. However, there have been no studies that examined the application of different ML classification algorithms in agricultural settings to classify various output variables using a wide range of input variables. In this study, twenty-four ML classification algorithms were implemented on a dataset from three locations within the Upper Parkhill watershed, an agricultural watershed in southern Ontario, Canada. Nutrient concentrations in surface water were classified using geochemical and physical water parameters of surface water and groundwater (e.g., pH), climate and field conditions as the input variables. The performance of these algorithms was evaluated using four evaluation metrics (e.g., classification accuracy) to identify the optimal algorithm for classifying the output variables. Ensemble bagged trees was found to be the optimal ML algorithm for classifying nitrate concentration in surface water (accuracy of 90.9%), while the weighted KNN was the most appropriate algorithm for categorizing the total phosphorus concentration (accuracy of 87%). The ensemble subspace discriminant algorithm gave the highest overall classification accuracy for the concentration of soluble reactive phosphorus and total dissolved phosphorus in surface water with an accuracy of 79.2% and 77.9%, respectively. This study exemplifies that ML algorithms can be used to signify exceedance of recommended concentrations of nutrients in surface waters in agricultural watersheds. Results are useful for decision makers to develop nutrient management strategies.

Spatial Prediction of Current and Future Flood Susceptibility: Examining the Implications of Changing Climates on Flood Susceptibility Using Machine Learning Models

The main aim of this study was to predict current and future flood susceptibility under three climate change scenarios of RCP2.6 (i.e., optimistic), RCP4.5 (i.e., business as usual), and RCP8.5 (i.e., pessimistic) employing four machine learning models, including Gradient Boosting Machine (GBM), Random Forest (RF), Multilayer Perceptron Neural Network (MLP-NN), and Naïve Bayes (NB). The study was conducted for two watersheds in Canada, namely Lower Nicola River, BC and Loup, QC. Three statistical metrics were used to validate the models: Receiver Operating Characteristic Curve, Figure of Merit, and F1-score. Findings indicated that the RF model had the highest accuracy in providing the flood susceptibility maps (FSMs). Moreover, the provided FSMs indicated that flooding is more likely to occur in the Lower Nicola River watershed than the Loup watershed. Following the RCP4.5 scenario, the area percentages of the flood susceptibility classes in the Loup watershed in 2050 and 2080 have changed by the following percentages from the year 2020 and 2050, respectively: Very Low = -1.68%, Low = -5.82%, Moderate = +6.19%, High = +0.71%, and Very High = +0.6% and Very Low = -1.61%, Low = +2.98%, Moderate = -3.49%, High = +1.29%, and Very High = +0.83%. Likewise, in the Lower Nicola River watershed, the changes between the years 2020 and 2050 and between the years 2050 and 2080 were: Very Low = -0.38%, Low = -0.81%, Moderate = -0.95%, High = +1.72%, and Very High = +0.42% and Very Low = -1.31%, Low = -1.35%, Moderate = -1.81%, High = +2.37%, and Very High = +2.1%, respectively. The impact of climate changes on future flood-prone places revealed that the regions designated as highly and very highly susceptible to flooding, grow in the forecasts for both watersheds. The main contribution of this study lies in the novel insights it provides concerning the flood susceptibility of watersheds in British Columbia and Quebec over time and under various climate change scenarios.

A Spatial Decision Support Approach for Flood Vulnerability Analysis in Urban Areas: A Case Study of Tehran

Preparedness against floods in a hazard management perspective plays a major role in the pre-event phase. Hence, assessing urban vulnerability and resilience towards floods for different risk scenarios is a prerequisite for urban planners and decision makers. Therefore, the main objective of this study is to propose the design and implementation of a spatial decision support tool for mapping flood vulnerability in the metropolis of Tehran under different risk scenarios. Several factors reflecting topographical and hydrological characteristics, demographics, vegetation, land use, and urban features were considered, and their weights were determined using expert opinions and the fuzzy analytic hierarchy process (FAHP) method. Thereafter, a vulnerability map for different risk scenarios was prepared using the ordered weighted averaging (OWA) method. Based on our findings from the vulnerability analysis of the case study, it was concluded that in the optimistic scenario (ORness = 1), more than 36% of Tehran’s metropolis area was marked with very high vulnerability, and in the pessimistic scenario (ORness = 0), it was less than 1%was marked with very high vulnerability. The sensitivity analysis of our results confirmed that the validity of the model’s outcomes in different scenarios, i.e., high reliability of the model’s outcomes. The methodical approach, choice of data, and the presented results and discussions can be exploited by a wide range of stakeholders, e.g., urban planners, decision makers, and hydrologists, to better plan and build resilience against floods.

An Extended Watershed-Based AHP Model for Flood Hazard Estimation: Constraining Runoff Converging Indicators via MFD-Derived Sub-Watershed by Maximum Zonal Statistical Method

Floods threaten the sustainable development of areas with a high probability of hazard. A typical analytic hierarchy process (pixel-based AHP) based flood hazard estimation method may ignore the similar threat caused by neighborhood cells at the sub-watershed scale. This study proposed an extended Watershed-based Zonal Statistical AHP for flood hazard estimation: Constraining converging related indicators by the sub-watersheds (WZSAHP-RC) model to improve this gap. Before calculating the flood hazard index, the proposed model uses the sub-watershed derived by the multiple flow direction method as a based unit to calculate the maximum zonal statistical value of runoff converging indicators. Moreover, taking the Chaohu basin of Anhui in China as the case study, the validation flooding ground-truthing was constructed from GF-3, and Landsat OLI images of the flood event from 20 July to 24 July 2020, which is the biggest flood recorded by the Zhongmiao station, which recorded a new water level, 0.82 m higher than the historical record. Compared with the validation, the results indicated the proposed method could improve the correct ratio by 38% (from 22% to 60%) and the fit ratio by 17% (from 18% to 35%) when considering the predicted flood hazard levels of “High” and “Very High” as flooded areas. Moreover, the flood hazard map derived by WZSAHP-RC demonstrated greater consistency in the flooded districts filtered by Baidu News than the pixel-based AHP. It revealed that considering two- or even multi-dimensional homogeneity may help to improve the accuracy of flood hazard maps on a catchment scale.