Please use this identifier to cite or link to this item:
Title: Modeling reference evapotranspiration using hybrid artificial intelligence techniques in arid and semi-arid regions of India
Authors: Patil, Amit Prakash
Supervisors: Deka, Paresh Chandra
Keywords: Department of Applied Mechanics and Hydraulics;Evapotranspiration;Arid Region;Semi-arid Region;Factor Analysis;Wavelet Transform;ANN;ANFIS;LS- SVM
Issue Date: 2017
Publisher: National Institute of Technology Karnataka, Surathkal
Abstract: Evapotranspiration (ET) plays an important role in efficient crop water management. Accurate estimation of ET is a challenging task in developing countries like India, where the availability of meteorological data is often minimal. This study makes an attempt to evaluate the potential and applicability of hybrid Wavelet-Artificial Intelligence (AI) models for estimating reference crop evapotranspiration (ETo) in arid and semi-arid regions of India. The hybrid models were developed by using wavelet decomposed subseries of meteorological variables as inputs to the ANN, ANFIS and LS-SVM models. Performance of the proposed hybrid models was then compared to the classical AI models. The study used forty year weekly dataset from Jodhpur and Pali (arid region) weather station. Also, daily data for six years were obtained from Hyderabad and Kurnool weather station (semi-arid region). In absence of lysimeter data, ETo values are calculated by FAO-56PM equation. Prior to the development of models, factor analysis test was employed to identify the input combination that may yield more efficient model under limited data scenario. Additionally, the effectiveness of using ETo data from another station in the same climatic region (extrinsic data) was also evaluated. It is expected that the proposed hybrid models together with extrinsic input variables would provide efficient ETo estimation models. The performance of hybrid and classical AI models were compared using RMSE, NSE and threshold statistics. Scatter plots were used to evaluate the accuracies of the models and box plots were used to analyze the spread of the data points estimated by the models. The results show that the proposed AI models worked better at estimating weekly ETo in arid regions compared to estimating daily ETo in semi-arid regions. The hybrid AI models displayed a better performance compared to the classical AI models at all the stations. It was found that hybrid W-LSSVM was the best model for estimating ETo in both arid and semi-arid region. Further, it was observed that the use of extrinsic inputs delivered good results only in arid regions. It was also observed that in semi-arid regions, use of wavelet decomposed extrinsic data deteriorated the performance of some hybrid models.
Appears in Collections:1. Ph.D Theses

Files in This Item:
File Description SizeFormat 
135015AM13F04.pdf6.85 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.