Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin
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 classific...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/8/1570 |
| _version_ | 1797603135689064448 |
|---|---|
| author | Xiaodi Fu Guangyuan Kan Ronghua Liu Ke Liang Xiaoyan He Liuqian Ding |
| author_facet | Xiaodi Fu Guangyuan Kan Ronghua Liu Ke Liang Xiaoyan He Liuqian Ding |
| author_sort | Xiaodi Fu |
| collection | DOAJ |
| description | 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 F<sub>1</sub> 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. |
| first_indexed | 2024-03-11T04:26:09Z |
| format | Article |
| id | doaj.art-64b3f2c527c04c95b6dc57a6cc59abc6 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T04:26:09Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-64b3f2c527c04c95b6dc57a6cc59abc62023-11-17T21:48:59ZengMDPI AGWater2073-44412023-04-01158157010.3390/w15081570Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River BasinXiaodi Fu0Guangyuan Kan1Ronghua Liu2Ke Liang3Xiaoyan He4Liuqian Ding5State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing 100038, ChinaBeijing IWHR Corporation, Beijing 100048, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing 100038, ChinaFor 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 F<sub>1</sub> 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.https://www.mdpi.com/2073-4441/15/8/1570rain patternsdistribution over time characteristicsdynamic time planningLightGBMLSTMDecision Tree |
| spellingShingle | Xiaodi Fu Guangyuan Kan Ronghua Liu Ke Liang Xiaoyan He Liuqian Ding Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin Water rain patterns distribution over time characteristics dynamic time planning LightGBM LSTM Decision Tree |
| title | Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin |
| title_full | Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin |
| title_fullStr | Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin |
| title_full_unstemmed | Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin |
| title_short | Research on Rain Pattern Classification Based on Machine Learning: A Case Study in Pi River Basin |
| title_sort | research on rain pattern classification based on machine learning a case study in pi river basin |
| topic | rain patterns distribution over time characteristics dynamic time planning LightGBM LSTM Decision Tree |
| url | https://www.mdpi.com/2073-4441/15/8/1570 |
| work_keys_str_mv | AT xiaodifu researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin AT guangyuankan researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin AT ronghualiu researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin AT keliang researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin AT xiaoyanhe researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin AT liuqianding researchonrainpatternclassificationbasedonmachinelearningacasestudyinpiriverbasin |