Hybrid model of generative adversarial network and Takagi‐Sugeno for multidimensional incomplete hydrological big data prediction

Abstract

Summary The processing of rainfall‐runoff transmission in the catchment area is a very complex phenomenon, such as temporal and spatial changes of the catchment characteristics and uncertainties of rainfall patterns. To handle this challenge, data‐driven hydrologic models emerge rapidly for the rainfall runoff prediction. However, the incomplete hydrological data constrain the development of digital hydrologic model. This article proposes a rainfall‐runoff prediction method of coupling generative adversarial network (GAN) and Takagi‐Sugeno (T‐S) fuzzy model, in which the GAN is used to generate the data for completing the incomplete hydrological data, and the T‐S fuzzy model is utilized for forecasting the rainfall runoff. The presented method is examined by real data in Huaihe basin just considering the precipitation and streamflow. Experiments show that the model combined GAN and T‐S can achieve satisfactory prediction results.

A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning

“…This elucidates a significant reason why GRU appl garner less attention than LSTM in hydrological forecasting. At present, the applic GRUs in hydrological forecasting in the literature is mainly based on basic alg [74,94,95], although there are also many improved versions of the GRU, such as t rectional GRU [122,123] or versions with added attention mechanisms [124,125] types of DL algorithms, such as GANs, ResNets, and GNNs, have been utilized in logical forecasting, yielding more satisfactory prediction outcomes [107,110,113,1 For example, the emergence of the GAN is significant for dealing with missing hy ical data. However, the number of related research works on these topics remains particularly in terms of the thorough adaptation of algorithms to this research con Based on the above literature review, Table 3 lists a comparison of different variants of GRUs or other models for hydrological forecasting.…”

“…At present, the application of GRUs in hydrological forecasting in the literature is mainly based on basic algorithms [74,94,95], although there are also many improved versions of the GRU, such as the bidirectional GRU [122,123] or versions with added attention mechanisms [124,125]. Other types of DL algorithms, such as GANs, ResNets, and GNNs, have been utilized in hydrological forecasting, yielding more satisfactory prediction outcomes [107,110,113,117,118]. For example, the emergence of the GAN is significant for dealing with missing hydrological data.…”

“…Li et al [107] fused a GAN with a fuzzy inference model for predicting multidimensional incomplete hydrological big data. In the proposed fusion model, the GAN was utilized to generate data to complete the incomplete hydrological data; the fuzzy inference model was used for rainfall-runoff prediction.…”

Geospatial Artificial Intelligence (GeoAI) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends

“…Several examples show the advantages of incorporating GAN models in hydrological classification [267][268][269] or combining it with autoencoder [270]. Integrating GAN with an LSTM network model [271][272][273]; combining GAN with an ANN fuzzy model [274] was also found to improve the automated hydrological and weather prediction using satellite data.…”