Prediction Map of Rainfall Classification Using Random Forest and Inverse Distance Weighted (IDW)

Noor, Ibnu Muzakky M.; Prasetyowati, Sri Suryani; Sibaroni, Yuliant

doi:10.47065/bits.v4i2.1978

Cited by 6 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The onset dates, cessation dates, and the length of rainy season deduced from OBS are spatialized using inverse distance weighted (IDW) interpolation to 1 degree by 1 degree resolution. IDW was predominantly used to interpolate rainfall as Chen and Liu (2012), Muzakky et al (2022), and de Oliveira Aparecido et al (2022) used it to estimate spatial rainfall in Tawain, Indonesia, and Brazil, respectively. This step converts the onset dates, cessation dates, and length of rainy season deduced from OBS to have the same resolution as CMIP6 under SSP245 and SSP585 scenarios.…”

Section: Methodsmentioning

confidence: 99%

Rainy season and crop calendars comparison between past (1950–2018) and future (2030–2100) in Madagascar

Randriamarolaza,

Aguilar

2023

Meteorological Applications

View full text Add to dashboard Cite

This paper analyzes rainfall data to characterize the rainy season and define rice and maize crop calendars for current and future conditions in Madagascar. The daily rainfall data are taken from observational climate records and climate model simulations from the CMIP6 under the SSP245 and SSP585 scenarios. Rainy season characteristics are calibrated to fit rice and maize crop growth stages. The comparison between the past (1950–2018) and the future (2030–2100) highlights changes in the onset and cessation dates, which happen later and earlier, respectively. This causes the reduction of the rainy season duration, which affects the rice and maize crop calendars, especially its sowing or seeding periods. The worst (best) case is mainly observed in the southeast (southwest). On the one hand, the southwestern region may need to adapt to grow rice and maize crops with short or medium crop cycles in the future. In the Highland or Central land, the length of the sowing or seeding period increases. On the other hand, the North and East face a significant reduction in the length of the sowing or seeding period. Rice endures more than maize. Growing rice crops twice a year may not be possible in the future. But rather, we observe minor changes in the West. Our analysis suggests the imperative necessity to advise smallholder farmers to rely on short crop cycle varieties of rice and maize crops. Predominantly, the harvesting period is postponed. It is recommended to carefully consider our results for the definition of food policies.

show abstract

Section: Methodsmentioning

confidence: 99%

Rainy season and crop calendars comparison between past (1950–2018) and future (2030–2100) in Madagascar

Randriamarolaza,

Aguilar

2023

Meteorological Applications

View full text Add to dashboard Cite

show abstract

“…( 10), while the variable Y2 is converted first as stated in Eq. (11) to allow the evaluation of scattering from the normal conditions. The average values for Y1 and Y2 are the same as shown in Eqs.…”

Section: Mahalanobis Distance =mentioning

confidence: 99%

“…Predicting rainfall has become increasingly important due to its impact on various sectors, such as agriculture [8], aquaculture [9], and the economy [10]. Factors such as the area where rainfall occurs, global heat, and indirect parameters associated with rainfall make it necessary to effectively predict rainfall from satellite images [11]. Therefore, developing rainfall prediction approaches that can determine when and what type of rain will occur is essential [12].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Rainfall Trends using Mahalanobis-Taguchi System

Mohd Jamil,

Abu,

Mohd Zaini

et al. 2024

J. Eng. Technol. Sci.

View full text Add to dashboard Cite

Full comprehension of precipitation patterns is crucially needed, especially in Pekan, a district in Pahang, Malaysia. The area is renowned for its elevated levels of precipitation, making it imperative to precisely categorize and enhance the analysis of rainfall patterns to facilitate effective resource allocation, agricultural productivity, and catastrophe readiness. The variability of rainfall patterns is contingent upon geographical location, necessitating the collection of a comprehensive data set that includes several characteristics that influence precipitation to make reliable predictions. Data were collected from the Vantage Pro2 weather station, which is located on the UMP Pekan campus. This study used the RT method to classify rainfall and T-Method 1 to determine the degree of contribution of each parameter. Significant parameters were validated using a data set from the same type of weather station but in a different district. The results showed that the Mahalanobis-Taguchi Bee Algorithm (MTBA) is more effective than the Mahalanobis-Taguchi System (MTS) in finding the significant parameters, but the parameters were a subset of MTS Teshima. Finally, the validation with T mean-based error (Tmbe) using Mean Absolute Error (MAE) revealed a pattern of errors to provide insight to find the significant parameters of MTS.

show abstract

“…The Random Forest Regressor shows the impressive in regression, while the Gradient Boosting Tree classifier excels in classification. The model is noted for its user-friendliness and efficiency, proving reliable for predicting rainfall which is crucial for agriculture, aviation, and water management [3,4,5].…”

Section: Introductionmentioning

confidence: 99%

Prognostication of Weather Patterns using Meteorological Data and ML Techniques

Mathur,

Kumar,

Choudhury

2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

In the field of modern weather prediction, the accurate classification is essential, impacting critical sectors such as agriculture, aviation, and water resource management. This research presents a weather forecasting model employing two influential classifiers random forest and technique based on gradient boosting, both implemented using the Scikit-learn library. Evaluation is based on key metrics including F1 score, accuracy, recall, and precision, with Gradient Boosting emerging as the superior choice for precipitation prediction. The study examines the performance of Random Forest Regression, Gradient Boosting Regression, and Radial Basis Function Neural Network in forecasting precipitation, drawing on prior research that demonstrated the superiority of the Random Forest algorithm in terms of accuracy and speed. Ensemble methods, particularly the Voting Classifier, a fusion of Random Forest and Gradient Boosting, outperform individual models, offering a promising avenue for advancing weather classification.

show abstract

Prediction Map of Rainfall Classification Using Random Forest and Inverse Distance Weighted (IDW)

Cited by 6 publications

References 13 publications

Rainy season and crop calendars comparison between past (1950–2018) and future (2030–2100) in Madagascar

Rainy season and crop calendars comparison between past (1950–2018) and future (2030–2100) in Madagascar

Prediction of Rainfall Trends using Mahalanobis-Taguchi System

Prognostication of Weather Patterns using Meteorological Data and ML Techniques

Contact Info

Product

Resources

About