Analysis of spatio-temporal variations and change point detection in pan coefficients in the northeastern region of India

Srilakshmi, M. V.; Jhajharia, Deepak; Gupta, Shivam; Yurembam, Ghanashyam Singh; Patle, G. T.

doi:10.1007/s00704-021-03888-3

Cited by 7 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods and techniques are used to estimate the crop water requirement, of which the reference evapotranspiration (ET 0 ) is a reliable and standard practice. ET 0 is a parameter that could be employed for all the regions based on the local climatic parameters [3]. The estimation of models is classified as (a) fully physicallybased combination models that employ mass and energy conservation principles; (b) semiphysically based models that consider either mass or energy conservation; and (3) black-box models that are empirical in nature [4,5].…”

Section: Introductionmentioning

confidence: 99%

Predictive Modelling of Reference Evapotranspiration Using Machine Learning Models Coupled with Grey Wolf Optimizer

Heramb

Rao

Subeesh

et al. 2023

Water

View full text Add to dashboard Cite

Mismanagement of fresh water is a primary concern that negatively impacts agricultural productivity. Judicious use of water in agriculture is possible by estimating the optimal requirement. The present practice of estimating crop water requirements is using reference evapotranspiration (ET0) values, which is considered a standard method. Hence, predicting ET0 is vital in allocating and managing available resources. In this study, different machine learning (ML) algorithms, namely random forests (RF), extreme gradient boosting (XGB), and light gradient boosting (LGB), were optimized using the naturally inspired grey wolf optimizer (GWO) viz. GWORF, GWOXGB, and GWOLGB. The daily meteorological data of 10 locations falling under humid and sub-humid regions of India for different cross-validation stages were employed, using eighteen input scenarios. Besides, different empirical models were also compared with the ML models. The hybrid ML models were found superior in accurately predicting at all the stations than the conventional and empirical models. The reduction in the root mean square error (RMSE) from 0.919 to 0.812 mm/day in the humid region and 1.253 mm/day to 1.154 mm/day in the sub-humid region was seen in the least accurate model using the hyperparameter tuning. The RF models have improved their accuracies substantially using the GWO optimizer than LGB and XGB models.

show abstract

Section: Introductionmentioning

confidence: 99%

Predictive Modelling of Reference Evapotranspiration Using Machine Learning Models Coupled with Grey Wolf Optimizer

Heramb

Rao

Subeesh

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…It detects the change points in the middle of any time series (Jaiswal et al, 2015) and detects a significant change in the mean of a time series. This test is based on the rank of the series and ignores the normality of the series (Srilakshmi et al, 2022)…”

Section: Change Point Detection Using Pettit's Testmentioning

confidence: 99%

Long‐term (2001–2020) trend analysis of temperature and rainfall and drought characteristics by in situ measurements at a tropical semi‐arid station from southern peninsular India

Thotli

Gugamsetty

Kalluri

et al. 2022

Intl Journal of Climatology

View full text Add to dashboard Cite

With the effects of climate change prevailing worldwide, it is essential to understand the long-term rainfall and temperature trends at regional scales to plan for adaptation strategies. Investigating the temporal dynamics of meteorological variables in climate-induced changes, particularly in rain-fed agriculture countries such as India, is needful. The present study focused on the temporal variation of rainfall and temperature trends to analyse the drought characteristics over the past 20 years (2001-2020) using ground-based Automatic Weather Station (AWS) data at a semi-arid station Anantapur in southern peninsular India. The seasonal maximum mean temperature (T mean ) was observed in summer (32.20 ± 1.36 C), followed by the monsoon (29.08 ± 1.02 C), postmonsoon (26.45 ± 2.44 C), and winter (25.45 ± 1.01 C) during the study period. The Mann-Kendall trend test result showed the decreasing trend in seasonal mean temperature during the drying period (winter [−0.069 CÁyear −1 ] and summer [−0.081 CÁyear −1 ]) and increasing trend in the wetting period (monsoon [0.012 CÁyear −1 ] and postmonsoon [0.034 CÁyear −1 ]). On the other hand, the seasonal rainfall decreases in the postmonsoon (−2.276 mmÁyear −1 ) while increasing in winter (0.5 mmÁyear −1 ), summer (2.137 mmÁyear −1 ), and monsoon (6.901 mmÁyear −1 ) seasons. The annual trends of minimum, maximum, and mean monthly temperatures decrease at the rate of −0.121, −0.123, and −0.022 CÁyear −1 , respectively, while the rainfall increases at the rate of 8.979 mmÁyear −1 . Furthermore, the temporal evolution of meteorological drought characteristics was estimated with the help of the standardized precipitation index (SPI) and standardized precipitation evapotranspiration index (SPEI) on multiple timescales ranging from 1 to 24 months on a monthly basis during the study period. The 24-month SPI values showed that 1 "severely dry" and the 29 "moderately dry" long-term

show abstract

“…The non-parametric tests depend on observation ranks rather than precise values, efficiently mitigating the constraints associated with the data distribution. Several researchers have used non-parametric tests instead of parametric tests due to these rationalities (Ahmadi et al, 2018;Jhajharia et al, 2012;Srilakshmi et al, 2022;Zamani et al, 2017). A study to detect the temperature and pan evaporation trends in Godavari River involved the application of non-parametric Mann-Kendall's test, as outlined in studies by D. Jhajharia et al (2014) and subsequently by D. Jhajharia et al (2021).…”

Section: Introductionmentioning

confidence: 99%

Investigating river water quality assessment through non‐parametric analysis: A case study of the Godavari River in India

Modi,

Chintalacheruvu

2023

Environmental Quality Mgmt

View full text Add to dashboard Cite

This study examines temporal variations in water quality parameters of Godavari River. The present study examines the concentrations of seven water quality parameters, namely total alkalinity (Alk), calcium (Ca), chlorine (Cl), total hardness (Hard), magnesium (Mg), sodium (Na), and sulfate (SO4), using data from 1981 to 2005 at seven gauging stations, that is, Mancherial, Pathagudem, Nowrangpur, Jagdalpur, Perur, Konta, and Polavaram. A seasonal analysis (pre‐monsoon, monsoon, and post‐monsoon) is conducted to detect trends in water quality parameters. The study also uses normality tests Kolmogorov–Smirnov (K–S) and Shapiro–Wilk (S–W) which reveals nonnormal distribution in the majority of datasets, necessitating non‐parametric analysis. The concentration of Alk, Ca, and Hard is found to be significantly increasing trend at some stations during all three seasons, along with significantly decreasing trend found in the concentrations of Cl, Na, and SO4 using non‐parametric Mann–Kendall's (M–K) and Sen's Slope test. The concentration of Mg depicts mixed trends at different stations which may be due the variation in agricultural practices or industrial activities surrounding the stations. It is evident that none of the parameter exhibits statistically significant trends across all seasons at any station. The results of Sen's Slope test are found to be in good agreement with Mann–Kendall's test statistics. A second order auto‐regressive model (AR (2)) is successfully employed to predict and forecast the water quality parameters in present and future time steps. The authenticity of AR (2) model is assessed using Nash‐Sutcliffe (NSE) efficiency and coefficient of determination (R2). The values of NSE and R2 are found to be more than 0.85 for all parameters during all the three seasons, along with, the values of mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE). The results of coefficient of variation (CV) and persistence‐criterion (PC) also depicts that AR (2) can successfully be utilized in forecasting the water quality parameters. The research contributes insights for effective water resource management in Godavari River basin.

show abstract

Analysis of spatio-temporal variations and change point detection in pan coefficients in the northeastern region of India

Cited by 7 publications

References 41 publications

Predictive Modelling of Reference Evapotranspiration Using Machine Learning Models Coupled with Grey Wolf Optimizer

Predictive Modelling of Reference Evapotranspiration Using Machine Learning Models Coupled with Grey Wolf Optimizer

Long‐term (2001–2020) trend analysis of temperature and rainfall and drought characteristics by in situ measurements at a tropical semi‐arid station from southern peninsular India

Investigating river water quality assessment through non‐parametric analysis: A case study of the Godavari River in India

Contact Info

Product

Resources

About