An Application of Ensemble Spatiotemporal Data Mining Techniques for Rainfall Forecasting

Saubhagya, Shanthi; Tilakaratne, Chandima; Mammadov, Musa; Lakraj, Pemantha

doi:10.3390/engproc2023039006

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The demand predominantly increased resulting from massive rural electrification drives introduced in the country in the last decade (Gill et al, 2019;Saubhagya, 2020). Additionally, increased dependence on coal power from expensive sources and rise in other financings, administrative and general and human resources expenditures has been reasons responsible for an increased average cost of supply (Prayas (Energy Group), 2015; Nirula, 2019;Verma et al, 2020).…”

Section: Resource Scarcities Of the Discomsmentioning

confidence: 99%

Unveiling benefits through franchising in Indian power distribution: addressing the resources scarcity

Das

2021

JEAS

View full text Add to dashboard Cite

PurposeThe Indian power distribution companies are increasingly recognizing franchising for reviving their high loss-making rural pockets. The motivation for franchising has been a reduction of the franchisor's resource scarcity by bringing in operational efficiency and improved service quality to end consumers. However, there is a dearth of evidence on the influence of the franchisee's operations in addressing the resource scarcity of franchisors in predominantly rural areas. This study contributes towards filling the research gap.Design/methodology/approachA qualitative embedded multiple case study was conducted. The cases comprised two rural franchisees operating towards attaining the common goal. The study was built on archival analysis, personal observations and semi-structured interviews with the franchisors and franchisee officials across the organization's hierarchical levels. A conceptual model based on the review of prior literature formed the initial set of coding for the study. The data were presented based on within-case and across-case analysis.FindingsThe analysis revealed that the contract design impacts the requisite operational efficiency achievement. This variation could be elaborated by factors, such as system adaptation across organizational hierarchy, autonomy and independence, review and feedback systems, monitoring, a professional's attitude, bureaucracy, adaption with the local areas, risk sharing, incentives and compensation structure.Research limitations/implicationsThe study findings could be generalized to the extent of similar socio-economic conditions, prevailing governance mechanisms and law and orders. Additionally, since the law does not mandate the regulatory commissions to scrutinize the performance of the franchisees, the study was built on data shared by the franchisees and the discom. Further, this study considered the performance of only two performing franchisees. Matching these actualities with the discoveries of this study remains a continuing project as participation of private players is increasingly being recognized. Therefore, the insights drawn from this study could be used to improve the franchise model and can be scaled up across the nation, regions and sectors.Originality/valueThere is a dearth of literature on franchising in electricity distribution. This study is one of the first studies on studying the franchise system in the electricity distribution sector through the application of a well-accepted management theory.

show abstract

Section: Resource Scarcities Of the Discomsmentioning

confidence: 99%

Unveiling benefits through franchising in Indian power distribution: addressing the resources scarcity

Das

2021

JEAS

View full text Add to dashboard Cite

show abstract

Machine Learning Models for Identifying Patterns in GNSS Meteorological Data

Alvarez-Castillo,

Torres-Carrión,

Serrano-Agila

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Granger Causality-Based Forecasting Model for Rainfall at Ratnapura Area, Sri Lanka: A Deep Learning Approach

Saubhagya,

Tilakaratne,

Lakraj

et al. 2024

Forecasting

View full text Add to dashboard Cite

Rainfall forecasting, especially extreme rainfall forecasting, is one of crucial tasks in weather forecasting since it has direct impact on accompanying devastating events such as flash floods and fast-moving landslides. However, obtaining rainfall forecasts with high accuracy, especially for extreme rainfall occurrences, is a challenging task. This study focuses on developing a forecasting model which is capable of forecasting rainfall, including extreme rainfall values. The rainfall forecasting was achieved through sequence learning capability of the Long Short-Term Memory (LSTM) method. The identification of the optimal set of features for the LSTM model was conducted using Random Forest and Granger Causality tests. Then, that best set of features was fed into Stacked LSTM, Bidirectional LSTM, and Encoder-Decoder LSTM models to obtain three days-ahead forecasts of rainfall with the input of the past fourteen days-values of selected features. Out of the three models, the best model was taken through post hoc residual analysis and extra validation approaches. This entire approach was illustrated utilizing rainfall and weather-related measurements obtained from the gauging station located in the city of Ratnapura, Sri Lanka. Originally, twenty-three features were collected including relative humidity, ssunshine hours, and mean sea level pressure. The performances of the three models were compared using RMSE. The Bidirectional LSTM model outperformed the other methods (RMSE < 5 mm and MAE < 3 mm) and this model has the capability to forecast extreme rainfall values with high accuracy.

show abstract

An Application of Ensemble Spatiotemporal Data Mining Techniques for Rainfall Forecasting

Abstract: This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

Cited by 3 publications

References 19 publications

Unveiling benefits through franchising in Indian power distribution: addressing the resources scarcity

Unveiling benefits through franchising in Indian power distribution: addressing the resources scarcity

Machine Learning Models for Identifying Patterns in GNSS Meteorological Data

Granger Causality-Based Forecasting Model for Rainfall at Ratnapura Area, Sri Lanka: A Deep Learning Approach

Contact Info

Product

Resources

About