Kebakaran hutan merupakan salah satu bencana yang sangat merugikan di dunia, tak terkecuali di Indonesia. Berdasarkan laporan dari Kementrian Lingkungan Hidup dan Kehutanan total kebakaran hutan dan lahan dalam rentang 2015 – 2019 yang terbakar adalah seluas 1.6 juta (Ha) [1]. Beberapa faktor yang mempengaruhi terjadinya kebakaran hutan diantaranya adalah faktor alam dan manusia. Faktor alam seperti kondisi suhu, kelembapan, kemarau, Elnino, erupsi gunung dan petir, kemudian para peneliti menemukan fakta bahwa aktivitas manusia di hutan seperti pembukaan lahan, eksploitasi kayu, perburuan dan pembakaran memiliki efek kausalitas terhadap terjadinya kebakaran hutan khususnya di daerah yang masih mempunyai hutan yang luas. Beberapa penelitian telah dilakukan untuk mencegah terjadinya kebakaran hutan seperti dengan menggunakan Teknik Data Mining dan Machine Learning yakni dengan melakukan prediksi kapan terjadinya kebakaran hutan berdasarkan kondisi cuaca dan histori laporan kebakaran namun masih belum sempurna. Maka dari itu pada penelitian ini kami mengembangkan konsep sistem prediksi kebakaran hutan yang akan menjadi salah satu acuan kebijakan pemerintah dalam mengeluarkan kebijakan yang bersifat preventif. Dengan melakukan pemodelan menggunakan model Algoritma Random Forest pada data kebakaran hutan dari tahun ketahun diwilayah Indonesia diharapakan dapat membantu pemerintah dalam melakukan pencegahan kebakaran hutan dengan kebijakan hukumnya dan analisis yang ada bisa digunakan oleh Balai Besar Teknologi Modifikasi Cuaca (BBTMC) yang dapat membantu menentukan kapan modifikasi cuaca dilakukan.
Today the need for fruit consumption is increasing along with the increasing human population and awareness of the consumption of nutritious foods, apples are one of the most consumed fruits by humans worldwide. According to data quoted from the Indonesian National Statistics Center in 2021, apple production in 2021 decreased from the previous year from 519,531 tons to 509,544 tons. One of the causes of the decline in apple production is the presence of pests on the apple plant. At least there are several types of pests that can be identified on apple leaves, namely Apple Scrub (Venturia inaequalis), Apple Black Root (Botryosphaeria) and Apple Cedar/Rust (Gymnosporangium juniperi virginianae). The research stage begins with conducting several literature studies regarding related research, then formulating and validating the problem and starting to collect data from the Kaggle public dataset. Then in the experimental stage, the author divides the dataset into three parts with a percentage of 80% training data, 10% validation data and 10% testing data. The image classification method used is the Convolutional Neural Network (CNN) algorithm to create a model that can classify image data, the process of implementing the author uses the python programming language to build the model. The author conducted several experiments by making changes to several model parameters that affect the accuracy of the model. To evaluate the performance and accuracy of the model using a confusion matrix. The results of the study indicate that image size, data augmentation and the number of epochs greatly affect the accuracy of the model, from the test results the CNN model with the best accuracy is the model with the image size parameter 256x256, horizontal flip, vertical flip and random rotation data augmentation and the number of the 60th epoch has the highest accuracy rate of 99.66%. The results of this study are expected to be implemented in an application that can be used directly by farmers in detecting pests on apple plants quickly and accurately.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.