Integrated hydrodynamic and machine learning models for compound flooding prediction in a data-scarce estuarine delta

Abstract

Abstract. Flood forecasting based on hydrodynamic modeling is an essential non-structural measure against compound flooding across the globe. With the risk increasing under climate change, all coastal areas are now in need of flood risk management strategies. Unfortunately, for local water management agencies in developing countries, building such a model is challenging due to the limited computational resources and the scarcity of observational data. We attempt to solve this issue by proposing an integrated hydrodynamic and machine learning (ML) approach to predict water level dynamics as a proxy for the risk of compound flooding in a data-scarce delta. As a case study, this integrated approach is implemented in Pontianak, the densest coastal urban area over the Kapuas River delta, Indonesia. Firstly, we build a hydrodynamic model to simulate several compound flooding scenarios. The outputs are then used to train the ML model. To obtain a robust ML model, we consider three ML algorithms, i.e., random forest (RF), multiple linear regression (MLR), and support vector machine (SVM). Our results show that the integrated scheme works well. The RF is the most accurate algorithm to model water level dynamics in the study area. Meanwhile, the ML model using the RF algorithm can predict 11 out of 17 compound flooding events during the implementation phase. It could be concluded that RF is the most appropriate algorithm to build a reliable ML model capable of estimating the river's water level dynamics within Pontianak, whose output can be used as a proxy for predicting compound flooding events in the city.

Prediction of Rainfall and Water Discharge in The Jagir River Surabaya with Long-Short-Term Memory (LSTM)

“…Using the Variant Inflation Factor, Sampurno et al conducted a statistical analysis to analyze the multicollinearity between the predictor variables (Sampurno, Vallaeys, Ardianto, & Hanert, 2022). The researcher tested four kernels, namely linear, polynomial, radial basis, and sigmoid, and found that the radial kernel had the best performance in the SVM algorithm.…”

Mapping Compound Flooding Risks for Urban Resilience in Coastal Zones: A Comprehensive Methodological Review

“…Chondros (2021) proposed an integrated approach for flood warning applicable to the flood-prone coastal area of Rohimno, Crete, Greece, developing an ANN model and demonstrating the superior performance of the developed ANN [146]. In addition to ANNs, other ML models-such as random forests (RF) [147][148][149][150][151], the Gaussian process metamodel (GPM) [152], support-vector machine (SVM) [147,150], and recurrent neural networks (RNNs) [153]-have also been applied. The ML model can make full use of historical data without considering the physical process of flood formation and can quickly train, verify, test, and evaluate the risk of floods based only on the historical flood record dataset, which provides an easier-to-implement approach to flood prediction, with high performance and relatively little complexity compared to physical models [154].…”

A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years

“…The combination of hydrodynamic models and machine learning can improve analysis reliability and computational efficiency [157,158]. For example, his-torical data or simulated data from hydrodynamic models can be used to train machine learning models to predict wave heights [159,160], hurricane storm surge hazards [161,162], floods [163], erosion [164], and water level characteristics of storm surges [155]. Notably, a nearshore wave and hydrodynamic prediction model by Wei and Davison [165] based on Convolutional Neural Networks can accurately predict the propagation and fragmentation of waves on nearshore slopes, including detailed wave peak bending and separation.…”