Machine-learning algorithms for forecast-informed reservoir operation (FIRO) to reduce flood damages

Water is stored in reservoirs for various purposes, including regular distribution, flood control, hydropower generation, and meeting the environmental demands of downstream habitats and ecosystems. However, these objectives are often in conflict with each other and make the operation of reservoirs a complex task, particularly during flood periods. An accurate forecast of reservoir inflows is required to evaluate water releases from a reservoir seeking to provide safe space for capturing high flows without having to resort to hazardous and damaging releases. This study aims to improve the informed decisions for reservoirs management and water prerelease before a flood occurs by means of a method for forecasting reservoirs inflow. The forecasting method applies 1- and 2-month time-lag patterns with several Machine Learning (ML) algorithms, namely Support Vector Machine (SVM), Artificial Neural Network (ANN), Regression Tree (RT), and Genetic Programming (GP). The proposed method is applied to evaluate the performance of the algorithms in forecasting inflows into the Dez, Karkheh, and Gotvand reservoirs located in Iran during the flood of 2019. Results show that RT, with an average error of 0.43% in forecasting the largest reservoirs inflows in 2019, is superior to the other algorithms, with the Dez and Karkheh reservoir inflows forecasts obtained with the 2-month time-lag pattern, and the Gotvand reservoir inflow forecasts obtained with the 1-month time-lag pattern featuring the best forecasting accuracy. The proposed method exhibits accurate inflow forecasting using SVM and RT. The development of accurate flood-forecasting capability is valuable to reservoir operators and decision-makers who must deal with streamflow forecasts in their quest to reduce flood damages.

Evaluation of Urban Flood Control Project –Case Study at Bendung Watershed in Palembang City, Indonesia–

Palembang City locates on a lowland where the altitude is between 12 and 30m above sea level. There are many small rivers that flow into a main river, Musi river. Due to the topographical configuration and a seasonal heavy rainfall, those rivers had been overflowed and the city had an inundation disaster. Bendung watershed is one of the nineteen watersheds in Palembang City, and the watershed also experiences the inundation disaster frequently due to the flood caused by a poor river maintenance and drainage system.The local government of Palembang City has applied some flood control projects such as a normalization project to reduce the flood damages. These measures checked the river flow over the dike, but some areas still suffered from the flood damages due to their topography. Based on the current situation, this study evaluates the efficiency of the existing normalization project in this watershed to find a solution that reduces the flood in those areas. Furthermore, this study investigates the feasibility of infiltration-well system to overcome the flood in those areas. The feasibility study includes the cost and benefit analysis to realize the infiltration-well system for easing the inundation problem.Abstrak: Kota Palembang terletak di dataran rendah dengan ketinggian antara 12 sampai 30m di atas permukaan laut. Karena konfigurasi topografi dan curah hujan musiman yang tinggi, sebagian Kota Palembang sangat rentan terhadap genangan dan bencana banjir . DAS Bendung merupakan salah satu dari sembilan belas DAS yang ada di Kota Palembang, dan DAS tersebut juga sering mengalami bencana genangan akibat banjir yang disebabkan oleh sistem drainase yang buruk.Pemerintah Daerah Kota Palembang telah menerapkan beberapa proyek pengendalian banjir seperti proyek normalisasi sungai. Proyek ini cukup sukses mencegah air sungai bendung meluap melewati tanggul sungai tersebut, tetapi beberapa lokasi yang jauh dari sungai bendung masih mengalami genangan karena topografinya. Berdasarkan kondisi ini, studi ini mengevaluasi efisiensi proyek normalisasi di DAS ini untuk mencari solusi yang dapat mengurangi banjir di wilayah tersebut. Selanjutnya studi ini mengkaji kelayakan sistem sumur resapan untuk mengatasi banjir di wilayah tersebut. Studi kelayakan lain meliputi analisis biaya dan manfaat sistem sumur resapan untuk mengatasi masalah genangan.

Climate signals in river flood damages emerge under sound regional disaggregation

Climate change affects precipitation patterns. Here, we investigate whether its signals are already detectable in reported river flood damages. We develop an empirical model to reconstruct observed damages and quantify the contributions of climate and socio-economic drivers to observed trends. We show that, on the level of nine world regions, trends in damages are dominated by increasing exposure and modulated by changes in vulnerability, while climate-induced trends are comparably small and mostly statistically insignificant, with the exception of South & Sub-Saharan Africa and Eastern Asia. However, when disaggregating the world regions into subregions based on river-basins with homogenous historical discharge trends, climate contributions to damages become statistically significant globally, in Asia and Latin America. In most regions, we find monotonous climate-induced damage trends but more years of observations would be needed to distinguish between the impacts of anthropogenic climate forcing and multidecadal oscillations.