A Novel Integrated Learning Model for Rainfall Prediction CEEMD- FCMSE -Stacking

Scientific prediction of precipitation changes has important guiding value and significance for revealing regional spatial and temporal patterns of precipitation changes, flood climate prediction, etc. Based on the fact that CEEMD can effectively overcome the interference of modal aliasing and white noise, fine composite multi-scale entropy can reorganize the same FCMSE value to reduce the modal component and improve the computational efficiency, and Stacking ensemble learning can effectively and conveniently improve the fitting effect of machine learning, a rainfall prediction method based on CEEMD-fine composite multi-scale entropy and Stacking ensemble learning is constructed, and it is applied to the prediction of monthly precipitation in the Xixia. The results show that, under the same conditions, the CEEMD-RCMSE-Stacking model reduces the root mean square error by 83.48% and 62.08%, and the mean absolute error by 83.25% and 61.84%, respectively, compared with the single Stacking model and CEEMD-LSTM, while the goodness-of-fit coefficients improve by 15.94% and 2.34%, respectively, which means that the CEEMD-RCMSE-Stacking model has higher prediction performance. The CEEMD-RCMSE-Stacking model has higher prediction performance.

A case study of the impact of INSAT derived humidity profiles on precipitation forecast by limited area model

The impact of humidity profiles estimated from INSAT digital IR cloud imagery data on initial moisture analysis in the IMD's operational limited area forecast system has been investigated. Method for assimilation of humidity profiles data as pseudo observations in the analysis scheme has been developed and implemented in the regional analysis scheme. Verification of humidity analysis with this data has shown substantial improvements in the moisture analysis over the data sparse region of tropics. Impact of the improved humidity analysis on model predicted rainfall is examined. The experiments show improved rainfall prediction.

Indigenous Technical Knowledge based Rainfall Prediction: A Review

Indigenous technical knowledge (ITK) is the actual knowledge of a given population that reflects the experiences based on tradition and includes more recent experiences with modern technologies. Traditionally, farmers have used traditional knowledge to understand weather and climate patterns in order to make decisions about crop and irrigation cycles. This knowledge has been gained through many decades of experience and has been passed on from previous generations. The present study was undertaken with the objective of collection and documenting the indigenous technical knowledge of farmers regarding rainfall prediction based on abiotic and biotic factors which is being practiced generation after generation. Here in this paper an effort has been made to collect the abiotic and biotic factors predicting rainfall, as a part of ICAR sponsored NASF ad-hoc research project entitled “Developing climate resilient adaptive strategies for empowerment of farmers” which has been implemented in University of Agricultural Sciences, Dharwad from 2019 to 2022. Various indigenous technical knowledge are collected by analyzing the journals and newsletters, deep interaction with the farmers of study area, contacting the local resource persons and documenting oral histories without scientific validation. The study found that traditional methods of rainfall forecasting can be utilized for the purpose of short-term and long-term seasonal rainfall predictions by local communities. All available abiotic and biotic indigenous rainfall forecasting techniques may serve as alternative to modern technologies.

Water Erosion Monitoring and Prediction in Response to the Effects of Climate Change Using RUSLE and SWAT Equations: Case of R’Dom Watershed in Morocco

Soil erosion is an increasingly issue worldwide, due to several factors including climate variations and humans’ activities, especially in Mediterranean ecosystems. Therefore, the aim of this paper is: (i) to quantify and to predict soil erosion rate for the baseline period (2000–2013) and a future period (2014–2027), using the Revised Universal Soil Loss Equation (RUSLE) and the Soil and Water Assessment Tool (SWAT) model in the R’Dom watershed in Morocco, based on the opportunities of Remote Sensing (RS) techniques and Geographical Information System (GIS) geospatial tools. (ii) we based on classical statistical downscaling model (SDSM) for rainfall prediction. Due to the lack of field data, the model results are validated by expert knowledge. As a result of this study, it is found that both agricultural lands and bare lands are most affected by soil erosion. Moreover, it is showed that soil erosion in the watershed was dominated by very low and low erosion. Although the area of very low erosion and low erosion continued to decrease. Hence, we hereby envisage that our contribution will provide a more complete understanding of the soil degradation in this study area and the results of this research could be a crucial reference in soil erosion studies and also may serve as a valuable guidance for watershed management strategies.

Information Extraction from Agricultural and Weather Domain using Deep Learning Approach

India is an agricultural region and the economy of the country depends upon agriculture. Change in climatic parameters (like rainfall, soil, etc) directly affect the growth of crops. This parameter has an unswerving effect on the quantity of food production. Information extraction from the agricultural domain through rainfall prediction has been one of the most challenging issues around the world in recent years because of climatic changes. To evaluate the feasibility of rain by employing some data analytics and machine learning techniques are developed. This paper proposes an enhanced deep learning-based approach known as Deep Regression Network (DRN). The proposed DRN is a 6-layer deep neural network. The proposed algorithm trains and tests on the agricultural corpus, collected from Dehradun (India) region. The experimental outcomes state that the proposed DRN method attained a prediction accuracy approx 86.56%. The comparative analysis shows that the proposed method outperformed existing methods like Ensemble Neural Network, Naïve Bayes, KNN, and Weighted Self-Organizing Map.

Hydro-Meteorological Incident and Disaster Response in Sri Lanka. Case Study: 2016 May Rain Events

This paper investigates hydro-meteorological hazards faced by Sri Lanka, a lower-middle-income island country in Asia. It provides a case study of a major hydro-meteorological disaster incident that resulted in one of the largest landslides in the history of the country, the Post-Disaster Needs Assessment (PDNA) process, and the national disaster response. Rainfall and flood inundation data are provided for the whole country. The fact that data are held by several government agencies (namely Department of Meteorology, Department of Irrigation, and NBRO), somewhat coordinated by the Disaster Management Center (DMC) is shown. The need for more streamlined coordination of hydro-met data with online access of data for researchers is emphasized. The flood disaster situation and disaster declaration of the Western Province (which contributes nearly 40% of the GDP) is looked at, and evidence is presented to recommend a smaller governance unit for future disaster declarations, in order to bring aid to the places where it is needed and leaving other areas of the province to carry on with the normal economic activity. An example of the use of climate change scenarios in rainfall prediction is provided from a developed island nation (New Zealand). The need for Sri Lanka to increase its spending for hydro-met services (both infrastructure and skills) is highlighted (the global norm being 0.02 of GDP), as the return on such investment is tenfold.

Rainfall prediction optimization model in ten-day time step based on sliding window mechanism and zero sum game

Rainfall is a precious water resource, especially for Shenzhen with scarce local water resources. Therefore, an effective rainfall prediction model is essential for improvement of water supply efficiency and water resources planning in Shenzhen. In this study, a deep learning model based on zero sum game (ZSG) was proposed to predict ten-day rainfall, the regular models were constructed for comparison, and the cross-validation was performed to further compare the generalization ability of the models. Meanwhile, the sliding window mechanism, differential evolution genetic algorithm, and discrete wavelet transform were developed to solve the problem of data non-stationarity, local optimal solutions, and noise filtration, respectively. The k-means clustering algorithm was used to discover the potential laws of the dataset to provide reference for sliding window. Mean square error (MSE), Nash–Sutcliffe efficiency coefficient (NSE) and mean absolute error (MAE) were applied for model evaluation. The results indicated that ZSG could better optimize the parameter adjustment process of models, and improved generalization ability of models. The generalization ability of the bidirectional model was superior to that of the unidirectional model. The ZSG-based models showed stronger superiority compared with regular models, and provided the lowest MSE (1.29%), NSE (21.75%), and MAE (7.5%) in the ten-day rainfall prediction.