Version 1
: Received: 1 November 2024 / Approved: 1 November 2024 / Online: 1 November 2024 (18:11:50 CET)
How to cite:
Almeida, V. A. D.; Anochi, J. A.; Rozante, J. R.; Campos Velho, H. F. D. Machine Learning for Frost Prediction in a South America Region. Preprints2024, 2024110050. https://doi.org/10.20944/preprints202411.0050.v1
Almeida, V. A. D.; Anochi, J. A.; Rozante, J. R.; Campos Velho, H. F. D. Machine Learning for Frost Prediction in a South America Region. Preprints 2024, 2024110050. https://doi.org/10.20944/preprints202411.0050.v1
Almeida, V. A. D.; Anochi, J. A.; Rozante, J. R.; Campos Velho, H. F. D. Machine Learning for Frost Prediction in a South America Region. Preprints2024, 2024110050. https://doi.org/10.20944/preprints202411.0050.v1
APA Style
Almeida, V. A. D., Anochi, J. A., Rozante, J. R., & Campos Velho, H. F. D. (2024). Machine Learning for Frost Prediction in a South America Region. Preprints. https://doi.org/10.20944/preprints202411.0050.v1
Chicago/Turabian Style
Almeida, V. A. D., José Roberto Rozante and Haroldo Fraga de Campos Velho. 2024 "Machine Learning for Frost Prediction in a South America Region" Preprints. https://doi.org/10.20944/preprints202411.0050.v1
Abstract
A machine learning (ML)-based methodology for predicting frosts is applied to the southern and southeastern regions of Brazil, as well as to other countries including Uruguay, Paraguay, northern Argentina, and southeastern Bolivia. The machine learning model (using TensorFlow (TF)) was compared to the frost index IG (from the Portuguese: Índice de Geada) developed by the National Institute for Space Research (INPE, Brazil). The IG index is estimated using meteorological variables from a regional weather numerical model (RWNM). After calculating the two indices using the ML model and the RWNM, a voting committee (VC) was trained to select between the computed outputs. The AdaBoostClassifier algorithm was employed to implement the voting committee. The study area was subdivided into three distinct subregions: R1 (outside Brazil), R2 (the southern of Brazil), and R3 (the southeastern of Brazil). Two forecasting time scales were evaluated: 24 hours and 72 hours. The 24-hour forecasts from both approaches (TF and RWNM) exhibited similar performance in terms of the number of accurate predictions. However, in the region covering Uruguay and northern Argentina, the TensorFlow model demonstrated superior frost prediction accuracy. Additionally, the TensorFlow model outperformed the RWNM for the 72-hour forecast horizon.
Keywords
Frost index; frost prediction; deep learning; committee machine
Subject
Environmental and Earth Sciences, Atmospheric Science and Meteorology
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
