Klasifikasi Kebakaran Hutan dan Lahan Menggunakan Algoritma Naïve Bayes (Studi Kasus: Provinsi Riau)

Pratiwi, Trya Ayu; Irsyad, Muhammad; Kurniawan, Rahmad

doi:10.26418/justin.v9i2.42823

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Naïve Bayes algorithm is one of the classification algorithms based on the Bayesian theorem in statistics to predict the probability of a class [16]. Classification models using NB have the potential to be used effectively in fire event classification [17].…”

Section: Naïve Bayesmentioning

confidence: 99%

Predicting forest fire vulnerability using machine learning approaches in The Mediterranean Region: a case study of Türkiye

Purnama,

Jaya,

Syaufina

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Forest fires in Türkiye have devastated 2.5 million hectares of habitat over four decades, posing a grave threat to Mediterranean forest ecosystems. This study compares machine learning techniques: Decision Trees (DT), Naive Bayes (NB), Random Forest (RF), Artificial Neural Networks (ANN), and Support Vector Machines (SVM), for predicting forest fire vulnerability. Using a dataset encompassing various factors like precipitation, soil moisture, temperature, humidity, wind speed, land cover, elevation, aspect, slope, proximity to roads/electricity networks, and population density, the models were trained and tested. The dataset classified vulnerability into four classes: very low, low, moderate, and high. Evaluation metrics included overall accuracy, precision, sensitivity, F1-score, Cohen kappa, and cross-validation (CV).RF exhibited the highest performance (accuracy: 0.80, precision: 0.78, sensitivity: 0.80, F1-score: 0.78, Cohen kappa: 0.71, average CV: 0.71), predicting fire vulnerability classes very low (14.99%), low (0.68%), moderate (65.41%), and high (18.90%) with notable accuracy. DT yielded consistent results, while NB performed stably, though slightly lower than RF and DT. However, ANN and SVM demonstrated lower performance and higher variability. These findings advocate for RF as the most accurate algorithm for forest fire risk prediction, emphasizing its crucial role in proactive fire risk management strategies.

show abstract

Section: Naïve Bayesmentioning

confidence: 99%

Predicting forest fire vulnerability using machine learning approaches in The Mediterranean Region: a case study of Türkiye

Purnama,

Jaya,

Syaufina

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Hotspots are indicators of forest fires that detect an area with a relatively higher temperature than the surrounding temperature [10]. Hotspots are points on the image (pixels or sub-pixels) that have very high temperatures and are associated with active Earth surface fires [21].…”

Section: B Hotspotmentioning

confidence: 99%

“…A hotspot is a forest fire indicator that detects an area with a relatively higher temperature than the surrounding temperature [10]. The site is represented in a point with specific coordinates.…”

Section: Introductionmentioning

confidence: 99%

Predicting the Number of Forest and Land Fire Hotspot Occurrences Using the ARIMA and SARIMA Methods

Santoso,

Widodo

2024

SISFOKOM

View full text Add to dashboard Cite

Forests are an area and part of the environmental cycle that is very important for survival because forests are areas on Earth that regulate the balance of the ecosystem. Forest fires rank second only to illegal logging in Indonesia's list of forest destruction causes. Forest fires can occur due to two factors, namely natural and human factors. Therefore, the hotspot factor that can cause forest fires is an independent variable. The population of hotspots in the West Kalimantan region in 2020 amounted to 1,416 spots. This study aims to predict the number of hotspot occurrences on land and forests that cause fires before the fires spread and are challenging to overcome or extinguish. The method to indicate the number of hotspot occurrences uses the Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) methods. Modeling ARIMA (0,1,1) and SARIMA (0,1,1) (2,2,1)12 obtained Root Mean Square Error (RMSE) evaluation results for ARIMA of 6.61 while SARIMA of 7.61. The ARIMA's Mean Squared Error (MSE) evaluation value is 43.70, and the SARIMA is 58.05. Based on these results, it can be concluded that the ARIMA model provides excellent and accurate performance in describing the trend of hotspot events that will occur in the future with a smaller RMSE value compared to SARIMA.

show abstract

Klasifikasi Kebakaran Hutan dan Lahan Menggunakan Algoritma Naïve Bayes (Studi Kasus: Provinsi Riau)

Cited by 2 publications

References 3 publications

Predicting forest fire vulnerability using machine learning approaches in The Mediterranean Region: a case study of Türkiye

Predicting forest fire vulnerability using machine learning approaches in The Mediterranean Region: a case study of Türkiye

Predicting the Number of Forest and Land Fire Hotspot Occurrences Using the ARIMA and SARIMA Methods

Contact Info

Product

Resources

About