Faculty Publications

Now showing 1 - 3 of 3

Forecasting daily pan evaporation using hybrid model of wavelet transform and support vector machines
(Inderscience Publishers, 2015) Pammar, L.; Deka, P.C.
Providing accurate and reliable estimation of evaporation has been of a great importance and has become obvious in many water resources applications such as management of hydrologic, hydraulic and agricultural systems. Researchers are finding reliable method of forecasting of pan evaporation. It is also important because of its key role in the part of development and management of water resources in variedclimatic regions. The study includes exploring hybrid model wavelet and support vector machine in daily pan evaporation forecasting for the data recorded near 'Bajpe' of Dakshina Kannada District, of Karnataka State, India. The conjunction method is compared with the single support vector machine. Gamma test and the parameter optimisation are necessary for accurate results and validation, in view of that parameter optimisation with grid search is employed. The root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (CC) statistics are used for comparison of results obtained, which shows that the hybrid method could increase the forecast accuracy and perform better than the single support vector machine. © © 2015 Inderscience Enterprises Ltd.
Daily pan evaporation modeling in climatically contrasting zones with hybridization of wavelet transform and support vector machines
(Springer Verlag service@springer.de, 2017) Pammar, L.; Deka, P.C.
The estimation of evaporation has been under surveillance, which is being carried out by many researchers toward applications in the fields related to hydrology and water resources management. Due to complexities associated with its estimation, research has employed several modes via direct and indirect methods to estimate. Accurate estimations are still the thrust area of research in these fields. The pan evaporation estimations with the help of data modeling techniques have provided better results in the recent past. The advancement in the field of data modeling has introduced several techniques which can best fit the data type and provide accurate estimations. The novel gamma test (GT) was used to decide the best input–output combination. Parameter optimization was carried out by grid search. The developed models gave better estimations of pan evaporation, but exhibited some limitations with nonlinearity, and sparse and noisy data. These limitations paved way for data pre-processing techniques such as wavelet transform. This study made an attempt to explore hybrid modeling using discrete wavelet transform (DWT) and support vector machines (SVR) for pan evaporation estimation. Two stations representing contrasting climatic zones namely ‘Bajpe’ and ‘Bangalore’ located in the state of Karnataka, India, are selected in this study. The meteorological datasets recorded at these stations are analyzed using gamma test and grid search to use the best input–output combinations for the models. The modeled pan evaporation estimations are very promising toward ever demanding accuracy expected in the associated fields. © 2017, The International Society of Paddy and Water Environment Engineering and Springer Japan.
Remote sensing and machine learning based framework for the assessment of spatio-temporal water quality in the Middle Ganga Basin
(Springer Science and Business Media Deutschland GmbH, 2022) Krishnaraj, A.; Honnasiddaiah, R.
Understanding the dynamics of water quality in any water body is vital for the sustainability of our water resources. Thus, investigating spatio-temporal changes of dominant water quality parameters (WQPs) in any study is indeed critical for proposing the appropriate treatment for the water bodies. Traditionally, concentrations of WQPs have been measured through intensive fieldwork. Additionally, many studies have attempted to retrieve concentrations of WQPs from satellite images using regression-based methods. However, the relationship between WQPs and satellite data is complex to be modeled accurately by using simple regression-based methods. Our study attempts to develop a machine learning model for mapping the concentrations of dominant optical and non-optical WQPs such as electrical conductivity (EC), pH, temperature (Temp), total dissolved solids (TDS), silicon dioxide (SiO2), and dissolved oxygen (DO). In this context, a remote sensing framework based on the extreme gradient boosting (XGBoost) and multi-layer perceptron (MLP) regressor with optimized hyper parameters (HPs) to quantify concentrations of different WQPs from the Landsat-8 satellite imagery is developed. We evaluated six years of satellite data stretching spatially from upstream to downstream Ankinghat to Chopan (20 stations under Central Water Commission (CWC), Middle Ganga Basin) for characterizing the trends of dominant physico-chemical WQPs across the four clusters identified in our previous study. Through the developed XGBoost and MLP regression models between measured WQPs and the reflectance of the pixels corresponding to the sampling stations, a significant coefficient of determination (R2) in the range of 0.88–0.98 for XGBoost and 0.72–0.97 for MLP were generated, with bands B1–B4 and their ratios more consistent. Indeed, these findings indicate that from a small number of in-situ measurements, we can develop reliable models to estimate the spatio-temporal variations of physico-chemical and biological WQPs. Therefore, models generated from Landsat-8 could facilitate the environmental, economic, and social management of any waterbody. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results