Search

Water scarcity is the most obstacle faced by irrigation water requirements, likewise, limited available meteorological data to calculate reference evapotranspiration. Consequently, the focal aims of the investigation are to assess the potential of machine learning models in forecasting irrigation water requirements (IWR) of snap beans by evolving multi-scenarios of inputs parameters to figure out the impact of meteorological, crop, and soil parameters on IWR. Six models were applied, support vector regressor (SVR), random forest (RF), deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and Hybrid CNN-LSTM. Ten variables including maximum and minimum temperature, Relative humidity, wind speed, precipitation, root depth, basal crop coefficient, soil evaporation, a fraction of surface wetted and, exposed and soil wetted fraction were used as the input data for models with their combination, 8 input scenarios were designed. Overall models, the best scenario was scenario 4 (relative humidity, wind speed, basal crop coefficient, soil evaporation), however, the best scenario for DNN and RF model was scenario 7 (root depth, basal crop coefficient, soil evaporation, fraction of surface wetted, exposed and soil wetted fraction). While the weakest one was the group of climatic factors in scenario 6 (maximum temperature, minimum temperature, relative humidity, wind speed, and precipitation). Among the models, the hybrid LTSM & CNN was the most accurate and the SVR model had the lowest estimation accuracy. The outcomes of this research work could set up a modeling strategy that would set in motion the improvement of efforts to identify the shortages in IWR forecasting, which sequentially may support alleviation strategies such as policies for sustainable water use and water resources management. The current approach was promising and has research value for other similar regions. [ABSTRACT FROM AUTHOR]

Evaporation is one of the most important parameters of meteorological science. Therefore, predicting evaporation is necessary for both water resources and planning management. The present study uses Bayesian Model Averaging (BMA) based on developed and optimized Kernel Extreme Learning Machine (KELM) models for predicting daily evaporation in different provinces of Iran with different climates. The Water Strider Algorithm, Salp Swarm Algorithm, Shark Algorithm, and Particle Swarm Optimization were combined with the KELM to predict daily evaporation in the Hormozgan, Mazandaran, Fars, Yazd, and Isfahan provinces. The models' inputs were average temperature, rainfall, number of sunny hours, wind speed, and relative humidity. The introducing a new hybrid gamma test for determining the adequate inputs, using hybrid and optimized KELM based on developing ELM for predicting evaporation, integrating individual models for predicting evaporation, and quantifying the uncertainty of outputs are the main innovations of the current study. Multiple error indices were used to evaluate the ability of models for predicting evaporation. The standalone and optimized KELM models were used to predict daily evaporation in the first level. In the next level, the BMA based on outputs of standalone and optimized KELM models predicted daily pan evaporation. The general results indicated that the BMA provided the best accuracy among other models in all stations. This study also introduced the new hybrid gamma test (GT-WSA) for choosing the best input combinations. The hybrid GT-WSA gave the best input combination without computing all input combinations (25 − 1). The uncertainty analysis of models also indicated that the uncertainty of BMA and optimized KELM models was lower than that of the KELM model. [ABSTRACT FROM AUTHOR]

This paper aims to find probabilities of extreme values of the air temperature for the Cerrado, Pantanal and Atlantic Forest biomes in Mato Grosso do Sul in Brazil. In this case a maximum likelihood estimation was employed for the probability distributions fitting the extreme monthly air temperatures for 2007–2018. Using the Extreme Value Theory approach this work estimates three probability distributions: the Generalized Distribution of Extreme Values (GEV), the Gumbel (GUM) and the Log-Normal (LN). The Kolmogorov–Smirnov test, the corrected Akaike criterion AICc, the Bayesian information criterion BIC, the root of the mean square error RMSE and the determination coefficient R2 were applied to measure the goodness-of-fit. The estimated distributions were used to calculate the probabilities of occurrence of maximum monthly air temperatures over 28–32 °C. Temperature predictions were done for the 2-, 5-, 10-, 30-, 50- and 100-year return periods. The GEV and GUM distributions are recommended to be used in the warmer months. In the coldest months, the LN distribution gave a better fit to a series of extreme air temperatures. Deforestation, combustion and extensive fires, and the related aerosol emissions contribute, alongside climate change, to the generation of extreme air temperatures in the studied biomes. [ABSTRACT FROM AUTHOR]

The aim of this paper is to investigate the teleconnection of large-scale climatic signals with river flow discharge in northern Iran. To this end, the Garmrud, Alishrud, and Babolrud rivers were selected: their monthly data set during the years 1993–2018 was received from the regional water company of the Mazandaran Province. Climate indices including the Southern Oscillation Index, extreme eastern tropical Pacific sea surface temperature (Niño 1 + 2), Global Mean Temperature Index, North Pacific pattern (NP), Pacific Decadal Oscillation, and North Atlantic Oscillation were investigated. The results of the cross-correlation, and the Spearman's test showed that there is a significant relationship at a 0.01 level between the indices and the river flow discharge. The most correlated indices were the NP and Niño 1 + 2. The NP index was inversely correlated and the Niño 1 + 2 was directly correlated with the rivers' flow variations, and the time lag of these two indices' maximum effectiveness was 2 months and 1 month, respectively. The adaptive neuro-fuzzy inference system and multilayer perceptron (MLP) models were used as the predictor models. The inputs were selected from the time lags of both river discharge and climatic indices. According to the normalized root mean square error (NRMSE) values (0.14–0.22), the predictions are evaluated as having moderate and appropriate qualities. The best performance of all models, R = 0.824 and RMSE = 0.350 CMS, was achieved for the MLP model. The results showed that consideration of the climatic indices as inputs may improve monthly flow predictability by an average of 24.1% (11.4–38.4% among the rivers and models). [ABSTRACT FROM AUTHOR]

Background: River damming inevitably reshapes water thermal conditions that are important to the general health of river ecosystems. Although a lot of studies have addressed the damming's thermal impacts, most of them just assess the overall effects of climate variation and human activities on river thermal dynamics. Less attention has been given to quantifying the impact of climate variation, damming and flow regulation, respectively. In addition, for rivers that have already faced an erosion problem in downstream channels, an adjustment of the hydroelectric power plant operation manner is expected, which reinforces the need for understanding of flow regulation's thermal impact. To fill this gap, an air2stream-based approach is proposed and applied at the Włocławek Reservoir in the Vistula River in Poland. Results: In the years of 1952–1983, downstream river water temperature rose by 0.31 ℃ after damming. Meanwhile, the construction of dam increased the average annual water temperature by 0.55 ℃, while climate change oppositely made it decreased by 0.26 ℃. In addition, for the seasonal impact of damming, autumn was the most affected season with the warming reached 1.14 ℃, and the least affected season was winter when water temperature experienced a warming of 0.1 ℃. The absolute values of seasonal average temperature changes due to flow regulation were less than 0.1 ℃ for all the seasons. Conclusions: The impacts of climate variation, damming, and flow regulation on river water temperatures can be evaluated reasonably on the strength of the proposed methodology. Climate variation and damming led to general opposite impacts on the downstream water temperature at the Włocławek Reservoir before 1980s. It is noted that the climate variation impact showed an opposite trend compared to that after 1980s. Besides, flow regulation below dam hardly affected downstream river water temperature variation. This study extends the current knowledge about impacts of climate variation and hydromorphological conditions on river water temperature, with a study area where river water temperature is higher than air temperature throughout a year. [ABSTRACT FROM AUTHOR]