Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin

Abstract

For the purpose of improving the scientific nature, reliability, and accuracy of flood forecasting, it is an effective and practical way to construct a flood forecasting scheme and carry out real-time forecasting with consideration of different rain patterns. The technique for rain pattern classification is of great significance in the above-mentioned technical roadmap. With the rapid development of artificial intelligence technologies such as machine learning, it is possible and necessary to apply these new methods to assist rain classification applications. In this research, multiple machine learning methods were adopted to study the time-history distribution characteristics and conduct rain pattern classification from observed rainfall time series data. Firstly, the hourly rainfall data between 2003 and 2021 of 37 rain gauge stations in the Pi River Basin were collected to classify rain patterns based on the universally acknowledged dynamic time warping (DTW) algorithm, and the classifications were treated as the benchmark result. After that, four other machine learning methods, including the Decision Tree (DT), Long- and Short-Term Memory (LSTM) neural network, Light Gradient Boosting Machine (LightGBM), and Support Vector Machine (SVM), were specifically selected to establish classification models and the model performances were compared. By adjusting the sampling size, the influence of different sizes on the classification was analyzed. Intercomparison results indicated that LightGBM achieved the highest accuracy and the fastest training speed, the accuracy and F1 score were 98.95% and 98.58%, respectively, and the loss function and accuracy converged quickly after only 20 iterations. LSTM and SVM have satisfactory accuracy but relatively low training efficiency, and DT has fast classification speed but relatively low accuracy. With the increase in the sampling size, classification results became stable and more accurate. Besides the higher accuracy, the training efficiency of the four methods was also improved.

An Improved Flood Susceptibility Assessment in Jeddah, Saudi Arabia, Using Advanced Machine Learning Techniques

“…Physically-based models work on parameters of water surface evaluation (WSE), depth of rivers, water discharge, soil infiltration capacity, evapotranspiration, and rainfall runoff [4]. Physical models are further classified into three categories: traditional, pattern classification, and rainfall runoff [5]. The pattern classification model categorizes geohydrological data into a land of water bodies and non-water bodies [6].…”

Rainfall Pattern Construction Method Based on DTW-HCA and Urban Flood Simulation: A Case Study of Nanchang City, China

“…Xu, et al [21] applied cumulative rainfall duration curves and fuzzy recognition methods to identify rainfall patterns of heavy rainfall events and analyzed peak characteristics of the heavy rainfall events of different durations after clustering. Fu, et al [22] used the dynamic time warping (DTW) algorithm to classify rainfall patterns and establish four separate rainfall type classification models using four different machine learning methods. The above-mentioned methods utilize clustering algorithms to compare and classify each rainfall event with the classic seven patterns [15].…”