Abstract. The Kapuas River delta is a unique estuary system on the western coast of the island of Borneo, Indonesia. Its hydrodynamics are driven by an interplay between storm surges, tides, and river discharges. These interactions are likely to be exacerbated by global warming, leading to more frequent compound flooding in the area. The mechanisms driving compound flooding events in the Kapuas River delta remain, however, poorly known. Here we attempt to fill this gap by assessing the interactions between river discharges, tides, and storm surges and how they can drive a compound inundation over the riverbanks, particularly within Pontianak, the main city along the Kapuas River. We simulated these interactions using the multi-scale hydrodynamic model SLIM (Second-generation Louvain-la-Neuve Ice-ocean Model). Our model correctly reproduces the Kapuas River's hydrodynamics and its interactions with tides and storm surge from the Karimata Strait. We considered several extreme-scenario test cases to evaluate the impact of tide–storm–discharge interactions on the maximum water level profile from the river mouth to the upstream part of the river. Based on the maximum water level profiles, we divide the Kapuas River's stream into three zones, i.e., the tidally dominated region (from the river mouth to about 30 km upstream), the transition region (from about 30 km to about 150 km upstream), and the river-dominated region (beyond 150 km upstream). Thus, the local water management can define proper mitigation for handling compound flooding hazards along the riverbanks by using this zoning category. The model also successfully reproduced a compound flooding event in Pontianak, which occurred on 29 December 2018. For this event, the wind-generated surge appeared to be the dominant trigger.

AbstrakPenelitian ini memanfaatkan model WRF-ARW (Weather Research and Forcasting -Advanced Research WRF) untuk memberikan gambaran mengenai kondisi atmosfer saat kejadian Borneo Vortex. Hasil visualisasi model WRF-ARW pada tanggal 28 Desember 2014 menunjukkan adanya vortex, dimana hal ini menimbulkan belokan angin dan arus konvergen di Laut Cina Selatan, Selat Karimata, dan Kalimantan bagian selatan. Selain itu kondisi atmosfer yang labil dan kelembaban udara yang tinggi saat itu, memicu terbentuknya awan-awan konvektif pada ketiga wilayah tersebut. Uji kehandalan sederhana pada model menunjukkan bahwa secara spasial model mampu memetakan wilayah-wilayah yang terdapat hujan dengan baik namun dari segi intensitas hujan, angka yang dihasilkan oleh model tergolong underestimate jika dibandingkan dengan data TRMM 3B42.

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.

Abstract. The Kapuas River delta is a unique estuary system on the west coast of Borneo Island, Indonesia. Its hydrodynamics is driven by an interplay between storm surges, tides, and rivers discharge. These interactions are likely to be exacerbated by global warming, leading to more frequent compound flooding in the area. The mechanisms driving compound flooding events in the Kapuas River Delta remain, however, poorly known. Here we attempt to fill this gap by assessing the interactions between river discharges, tides, and storm surges and how they can drive a compound inundation over the riverbanks, particularly within Pontianak, the main city along the Kapuas River. We simulated these interactions using the multi-scale hydrodynamic model SLIM. Our model correctly reproduces the Kapuas River’s hydrodynamics and its interactions with tides and storm surge from the Karimata Strait. We considered several extreme scenario test cases to evaluate the impact of tide-storm-discharge interactions on the maximum water level profile from the river mouth to the upstream part of the river. Based on the maximum water level profiles, we could divide the main branch of the Kapuas River’s stream into three zones, i.e., the tidally-dominated region (from the river mouth to about 4 km upstream), the mixed-energy region (from about 4 km to about 30 km upstream) and the river-dominated region (beyond 30 km upstream). Thus, the local water management can define proper mitigation for handling compound flooding hazards along the riverbanks by using this zoning category. The model also successfully reproduced a compound inundation event in Pontianak, which occurred on 29 December 2018. For this event, the wind-generated surge appeared to be the dominant trigger.

Abstract. Flood forecasting based on water level modeling is an essential non-structural measure against compound flooding over the globe. With its vulnerability increased under climate change, every coastal area became urgently needs a water level model for better flood risk management. 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. Here, we attempt to solve the issue by proposing an integrated hydrodynamic and machine learning approach to predict compound flooding in those areas. As a case study, this integrated approach is implemented in Pontianak, the densest coastal urban area over the Kapuas River delta, Indonesia. Firstly, we built a hydrodynamic model to simulate several compound flooding scenarios, and the outputs are then used to train the machine learning model. To obtain a robust machine learning model, we consider three machine learning algorithms, i.e., Random Forest, Multi Linear Regression, and Support Vector Machine. The results show that this integrated scheme is successfully working. The Random Forest performs as the most accurate algorithm to predict flooding hazards in the study area, with RMSE = 0.11 m compared to SVM (RMSE = 0.18 m) and MLR (RMSE = 0.19 m). The machine-learning model with the RF algorithm can predict ten out of seventeen compound flooding events during the testing phase. Therefore, the random forest is proposed as the most appropriate algorithm to build a reliable ML model capable of assessing the compound flood hazards in the area of interest.