Development of Rainfall Forecasting Model Using Machine Learning With Singular Spectrum Analysis

Abstract

Agriculture is the key point for survival for developing nations like India. For farming, rainfall is generally significant. Rainfall updates are help for evaluate water assets, farming, ecosystems and hydrology. Nowadays rainfall anticipation has become a foremost issue. Forecast of rainfall offers attention to individuals and knows in advance about rainfall to avoid potential risk to shield their crop yields from severe rainfall. This study intends to investigate the dependability of integrating a data pre-processing technique called singular-spectrum-analysis (SSA) with supervised learning models called least-squares support vector regression (LS-SVR), and Random-Forest (RF), for rainfall prediction. Integrating SSA with LS-SVR and RF, the combined framework is designed and contrasted with the customary approaches (LS-SVR and RF). The presented frameworks were trained and tested utilizing a monthly climate dataset which is separated into 80:20 ratios for training and testing respectively. Performance of the model was assessed using Root Mean Square Error (RMSE) and Nash–Sutcliffe Efficiency (NSE) and the proposed model produces the values as 71.6 %, 90.2 % respectively. Experimental outcomes illustrate that the proposed model can productively predict the rainfall. ABSTRAK:Pertanian adalah titik utama kelangsungan hidup negara-negara membangun seperti India. Untuk pertanian, curah hujan pada amnya ketara. Kemas kini hujan adalah bantuan untuk menilai aset air, pertanian, ekosistem dan hidrologi. Kini, jangkaan hujan telah menjadi isu utama. Ramalan hujan memberikan perhatian kepada individu dan mengetahui terlebih dahulu mengenai hujan untuk menghindari potensi risiko untuk melindungi hasil tanaman mereka dari hujan lebat. Kajian ini bertujuan untuk menyelidiki kebolehpercayaan mengintegrasikan teknik pra-pemprosesan data yang disebut analisis-spektrum tunggal (SSA) dengan model pembelajaran yang diawasi yang disebut regresi vektor sokongan paling rendah (LS-SVR), dan Random-Forest (RF), ramalan hujan. Menggabungkan SSA dengan LS-SVR dan RF, kerangka gabungan dirancang dan dibeza-bezakan dengan pendekatan biasa (LS-SVR dan RF). Kerangka kerja yang disajikan dilatih dan diuji dengan menggunakan set data iklim bulanan yang masing-masing dipisahkan menjadi nisbah 80:20 untuk latihan dan ujian. Prestasi model dinilai menggunakan Root Mean Square Error (RMSE) dan Nash – Sutcliffe Efficiency (NSE) dan model yang dicadangkan menghasilkan nilai masing-masing sebanyak 71.6%, 90.2%. Hasil eksperimen menggambarkan bahawa model yang dicadangkan dapat meramalkan hujan secara produktif.

Performance Evaluation of Machine Learning Regression Models for Rainfall Prediction

“…Leo Breiman (1996) developed the Random Forest (RF) ensemble machine learning algorithm for classification and regression applications which is based on decision tree predictors that employs numerous classification trees, hence the name random forest. Random Forest is one of the most widely used ML algorithm for rainfall forecasting (Reddy et al 2022, Meyer et al 2016, Yu et al 2017, Ouallouche et al 2018. It is a supervised algorithm employed for regression and classification problems.…”

“…The anticipation of rainfall is significant because severe rainfall events can cause serious harm to resources like the agriculture sector, human resources, and infrastructure. An early warning can limit the danger to life and property (Reddy et al 2022). Machine Learning (ML) techniques have gained significance in previous decades as a major tool being widely implemented on classification and regression-based problems.…”

A Novel Routing Protocol for Low-Energy Wireless Sensor Networks

“…Geographic Random Forwarding (GeRaf) will not focus on the energy consumption of the network but instead will select a good relay node between the forwarding multiple nodes. As the forwarder set is selected, an energy-efficient opportunistic routing scheme is proposed for the network, which puts nodes into sleep mode [16]. For energy savings, the SMAC method uses the MAC layer to select random nodes and turn them into sleep nodes, forming a sleeping schedule with their nearby nodes [17].…”

Automatic Detection of Maintenance Scenarios for Equipment and Control Systems in Industry

“…The study of time series is often used to predict and study the behavior of a signal. Many scientific works are devoted to this area of research, applying exactly the singular spectral decomposition method (SSA) [37,38]. For example, this work [39] performs forecasting of Iran's national accounts and [40] predicts the inflation rate in the United States.…”