1
|
Pinthong S, Ditthakit P, Salaeh N, Hasan MA, Son CT, Linh NTT, Islam S, Yadav KK. Imputation of missing monthly rainfall data using machine learning and spatial interpolation approaches in Thale Sap Songkhla River Basin, Thailand. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2022:10.1007/s11356-022-23022-8. [PMID: 36173524 DOI: 10.1007/s11356-022-23022-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Accepted: 09/10/2022] [Indexed: 06/16/2023]
Abstract
Missing rainfall data has been a prevalent issue and primarily interested in hydrology and meteorology. This research aimed to examine the capability of machine learning (ML) and spatial interpolation (SI) methods to estimate missing monthly rainfall data. Six ML algorithms (i.e. multiple linear regression (MLR), M5 model tree (M5), random forest (RF), support vector regression (SVR), multilayer perceptron (MLP), genetic programming (GP)) and four SI methods (i.e. arithmetic average (AA), inverse distance weighting (IDW), correlation coefficient weighted (CCW), normal ratio (NR)) were investigated and compared in their performance. The twelve rainfall stations, located in the Thale Sap Songkhla river basin and nearby basins, were considered as a study case. Tuning hyper-parameters for each ML method was conducted to get the most suitable model for the data sets considered. Three performance criteria matrices (i.e. NSE, OI, and r) were chosen, and the sum of those three performance criteria matrices was introduced for methods' performance comparison. The experimental results pointed out that selecting neighbouring stations were essential when applying SI methods, but not for the ML method. The overall performance showed ML better imputed missing monthly rainfall than SI due to overcoming spatial constraints. GP provided the highest performance by giving NSE = 0.825, OI = 0.877, and r = 0.909 for the training stage. Those values for the testing stage were 0.796, 0.852, and 0.902, respectively. It was followed by SVR-rbf, SVR-poly, and RF. NR provided the best performance among four SI methods, followed by CCW, AA, and IDW. When applying SI methods, it should contemplate a correlation between the target and neighbouring stations greater than 0.80.
Collapse
Affiliation(s)
- Sirimon Pinthong
- Center of Excellence in Sustainable Disaster Management, School of Engineering and Technology, Walailak University, Nakhon Si Thammarat, 80161, Thailand
| | - Pakorn Ditthakit
- Center of Excellence in Sustainable Disaster Management, School of Engineering and Technology, Walailak University, Nakhon Si Thammarat, 80161, Thailand.
| | - Nureehan Salaeh
- Center of Excellence in Sustainable Disaster Management, School of Engineering and Technology, Walailak University, Nakhon Si Thammarat, 80161, Thailand
| | - Mohd Abul Hasan
- Civil Engineering Department, College of Engineering, King Khalid University, Abha, 61421, Saudi Arabia
| | - Cao Truong Son
- Faculty of Natural Resources and Environment, Vietnam National University of Agriculture, Hanoi, 100000, Vietnam
| | - Nguyen Thi Thuy Linh
- Institute of Applied Technology, Thu Dau Mot University, Thủ Dầu Một, Binh Duong province, Vietnam
| | - Saiful Islam
- Civil Engineering Department, College of Engineering, King Khalid University, Abha, 61421, Saudi Arabia
| | - Krishna Kumar Yadav
- Faculty of Science and Technology, Madhyanchal Professional University, Ratibad, Bhopal, 462044, India
| |
Collapse
|
2
|
IHACRES, GR4J and MISD-based multi conceptual-machine learning approach for rainfall-runoff modeling. Sci Rep 2022; 12:12096. [PMID: 35840640 PMCID: PMC9287375 DOI: 10.1038/s41598-022-16215-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2022] [Accepted: 07/06/2022] [Indexed: 11/08/2022] Open
Abstract
As a complex hydrological problem, rainfall-runoff (RR) modeling is of importance in runoff studies, water supply, irrigation issues, and environmental management. Among the variety of approaches for RR modeling, conceptual approaches use physical concepts and are appropriate methods for representation of the physics of the problem while may fail in competition with their advanced alternatives. Contrarily, machine learning approaches for RR modeling provide high computation ability however, they are based on the data characteristics and the physics of the problem cannot be completely understood. For the sake of overcoming the aforementioned deficiencies, this study coupled conceptual and machine learning approaches to establish a robust and more reliable RR model. To this end, three hydrological process-based models namely: IHACRES, GR4J, and MISD are applied for runoff simulating in a snow-covered basin in Switzerland and then, conceptual models' outcomes together with more hydro-meteorological variables were incorporated into the model structure to construct multilayer perceptron (MLP) and support vector machine (SVM) models. At the final stage of the modeling procedure, the data fusion machine learning approach was implemented through using the outcomes of MLP and SVM models to develop two evolutionary models of fusion MLP and hybrid MLP-whale optimization algorithm (MLP-WOA). As a result of conceptual models, the IHACRES-based model better simulated the RR process in comparison to the GR4J, and MISD models. The effect of incorporating meteorological variables into the coupled hydrological process-based and machine learning models was also investigated where precipitation, wind speed, relative humidity, temperature and snow depth were added separately to each hydrological model. It is found that incorporating meteorological variables into the hydrological models increased the accuracy of the models in runoff simulation. Three different learning phases were successfully applied in the current study for improving runoff peak simulation accuracy. This study proved that phase one (only hydrological model) has a big error while phase three (coupling hydrological model by machine learning model) gave a minimum error in runoff estimation in a snow-covered catchment. The IHACRES-based MLP-WOA model with RMSE of 8.49 m3/s improved the performance of the ordinary IHACRES model by a factor of almost 27%. It can be considered as a satisfactory achievement in this study for runoff estimation through applying coupled conceptual-ML hydrological models. Recommended methodology in this study for RR modeling may motivate its application in alternative hydrological problems.
Collapse
|
3
|
Extensive Evaluation of Four Satellite Precipitation Products and Their Hydrologic Applications over the Yarlung Zangbo River. REMOTE SENSING 2022. [DOI: 10.3390/rs14143350] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
Satellite remote sensing precipitation products with high temporal–spatial resolution and large area coverage have great potential in hydrometeorological research. This paper analyzes the performance of four satellite products from 2000 to 2008 in the Yarlung Zangbo River Basin, namely the Tropical Rainfall Measuring Mission (TRMM), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN), Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), and Climate Prediction Center morphing method (CMORPH). The four products are evaluated from three aspects: spatial distribution, temporal characteristics, and hydrological simulation. The results show that: (1) the four products exhibit similar annual and daily precipitation patterns, with the highest daily precipitation accuracy concentrated in the center, followed by the east and west; (2) TRMM, CHIRPS, and CMORPH exhibit the largest positive bias for monthly precipitation estimation in December, while PERSIANN shows the largest positive bias in July. All products overestimate the precipitation of 0.1–5 mm/d, and underestimate the precipitation above 5 mm/d, especially for PERSIANN; (3) certain Products tend to perform better than others at elevations of 3000–4000 m and in relatively humid zones. TRMM shows relatively stable performance for various elevation and climate zones; (4) for hydrological model validation, TRMM has the best performance during the calibration period, although it is inferior to CHIRPS during the validation period. Overall, TRMM has the highest applicability in the Yarlung Zangbo River Basin; however, its impact on the uncertainty of hydrological modeling needs to be further studied.
Collapse
|