IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Computer Engineering Tehcnology
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Computer Engineering Tehcnology
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Rancang Bangun Sistem Pemantauan Cuaca Hiperlokal Berbasis Sensor GY-BME280 untuk Prediksi Jangka Pendek

      Thumbnail
      View/Open
      Cover (425.3Kb)
      Fulltext (4.659Mb)
      Lampiran (1.416Mb)
      Date
      2026
      Author
      BAIHAKI, RAIHAN ABRAR
      Fathonah, Lathifunnisa
      Metadata
      Show full item record
      Abstract
      Dinamika cuaca di Indonesia yang bersifat hiperlokal seringkali tidak tertangkap presisi oleh sistem pemantauan makro. Penelitian ini bertujuan merancang sistem pemantauan dan prediksi cuaca jangka pendek berskala hiperlokal terintegrasi sebagai peringatan dini presipitasi. Sistem dikembangkan menggunakan ESP32, sensor GY-BME280, dan GPS NEO-6M, dengan data yang divisualisasikan melalui aplikasi Flutter. Server menjalankan prediksi cuaca otomatis menggunakan algoritma empirical decision tree berdasarkan anomali parameter iklim permukaan bumi. Validasi sensor terhadap data Open-Meteo menunjukkan korelasi Pearson linier positif yang sangat kuat dengan tekanan bernilai 0,9138, suhu bernilai 0,8941, dan kelembapan bernilai 0,8476. Algoritma prediksi mencapai akurasi 93,91%, spesifisitas 95,55%, dan nilai F1 76,03%. Pengujian membuktikan sistem beroperasi optimal pada jendela pengamatan (lookback window) 60 menit, mencatat tingkat keberhasilan deteksi hujan 66,7% dengan rata-rata lead time 24,5 menit sebelum presipitasi.
       
      Hyperlocal weather dynamics in Indonesia are often imprecisely captured by macro-level monitoring systems. This study aims to design an integrated hyperlocal weather monitoring and short-term prediction system as an early warning for precipitation. The system was developed utilizing an ESP32, a GY-BME280 sensor, and a GPS NEO-6M module, with real-time data visualization via a Flutter application. The server executes automated weather predictions using an empirical decision tree algorithm based on surface climate parameter anomalies. Sensor validation against Open-Meteo data demonstrated very strong positive linear Pearson correlations with pressure on 0.9138, temperature on 0.8941, and humidity on 0.8476. The prediction algorithm achieved 93.91% accuracy, 95.55% specificity, and a 76.03% F1 score. Testing proved the system operates optimally with a 60-minute lookback window, recording a 66.7% rain detection success rate and an average lead time of 24.5 minutes prior to precipitation.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/174845
      Collections
      • UF - Computer Engineering Tehcnology [189]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository