Neural Network-Based Prediction Model for Evaporation Using Weather Data

Batra, Kamal; Gandhi, Parul

doi:10.1007/s40003-021-00537-z

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al (2019) [46] developed a method for post-processing seasonal GCM outputs to predict monthly and seasonal RET. Several models on heuristic and fuzzy-logic science for estimations of PE and RET and machine learning algorithms such as combined neural networks, genetic algorithm model, linear genetic programming, fuzzy genetic, adaptive neuro-fuzzy inference system, artificial neural networks, multilayer perceptron neural network, co-active neuro-fuzzy inference system, radial basis neural network and self-organizing map neural network showed high accuracy in different climate zones [15,[47][48][49][50][51].…”

Section: Developments In Et Measurement and Estimationmentioning

confidence: 99%

Evapotranspiration Trends and Interactions in Light of the Anthropogenic Footprint and the Climate Crisis: A Review

Dimitriadou

Nikolakopoulos

2021

Hydrology

View full text Add to dashboard Cite

Evapotranspiration (ET) is a parameter of major importance participating in both hydrological cycle and surface energy balance. Trends of ET are discussed along with the dependence of evaporation to key environmental variables. The evaporation paradox can be approached via natural phenomena aggravated by anthropogenic impact. ET appears as one of the most affected parameters by human activities. Complex hydrological processes are governed by local environmental conditions thus generalizations are difficult. However, in some settings, common hydrological interactions could be detected. Mediterranean climate regions (MCRs) appear vulnerability to the foreseen increase in ET, aggravated by precipitation shifting and air temperature warming, whereas in tropical forests its role is rather beneficial. ET determines groundwater level and quality. Groundwater level appeared to be a robust predictor of annual ET for peatlands in Southeast Asia. In semi-arid to arid areas, increases in ET have implications on water availability and soil salinization. ET-changes after a wildfire can be substantial for groundwater recharge if a canopy-loss threshold is surpassed. Those consequences are site-specific. Post-fire ET rebound seems climate and fire-severity-dependent. Overall, this qualitative structured review sets the foundations for interdisciplinary researchers and water managers to deploy ET as a means to address challenging environmental issues such as water availability.

show abstract

Section: Developments In Et Measurement and Estimationmentioning

confidence: 99%

Evapotranspiration Trends and Interactions in Light of the Anthropogenic Footprint and the Climate Crisis: A Review

Dimitriadou

Nikolakopoulos

2021

Hydrology

View full text Add to dashboard Cite

show abstract

“…(ii) BP neural network A back propagation neural network (BP) is a kind of multi-layer feedforward neural network [30]. Its main characteristic is that the signal propagates forward and the error propagates back.…”

Section: Machine Learning Algorithm (I) Random Forestmentioning

confidence: 99%

Trends and Changes in Hydrologic Cycle in the Huanghuaihai River Basin from 1956 to 2018

Yang

Bao

Wang

et al. 2022

Water

View full text Add to dashboard Cite

The Huanghuaihai River Basin (HRB) is one of the most prominent areas of water resource contradiction in China. It is of great significance to explore the relationship between water balance in this area for a deep understanding of the response of the water cycle to climate change. In this study, machine learning methods are used to prolong the actual evapotranspiration (ET) of the basin on the time scale and explore water balances calculated from various sources. The following conclusions are obtained: (1) it is found that the simulation accuracy of Global Land Evaporation Amsterdam Model (GLEAM) products in HRB is good. The annual average ET spatial distribution tends to increase from northwest to southeast; (2) three machine learning algorithms are used to construct the ET calculation model. The correlation coefficients of the three methods are all above 0.9 and the mean relative error values of random forest (RF) are all less than 30%. The RF has the best effect; (3) the relative errors of water balance in HRB from 1956–1979, 1980–2002 and 2003–2018 are less than ±5%, which indicates that the calculation of each element of the water cycle in the study area can well reflect the water balance relationship of the basin.

show abstract

Neural Network-Based Prediction Model for Evaporation Using Weather Data

Cited by 2 publications

References 7 publications

Evapotranspiration Trends and Interactions in Light of the Anthropogenic Footprint and the Climate Crisis: A Review

Evapotranspiration Trends and Interactions in Light of the Anthropogenic Footprint and the Climate Crisis: A Review

Trends and Changes in Hydrologic Cycle in the Huanghuaihai River Basin from 1956 to 2018

Contact Info

Product

Resources

About