Cargando…
Frost prediction using machine learning and deep neural network models
This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9878450/ https://www.ncbi.nlm.nih.gov/pubmed/36714205 http://dx.doi.org/10.3389/frai.2022.963781 |
_version_ | 1784878487347134464 |
---|---|
author | Talsma, Carl J. Solander, Kurt C. Mudunuru, Maruti K. Crawford, Brandon Powell, Michelle R. |
author_facet | Talsma, Carl J. Solander, Kurt C. Mudunuru, Maruti K. Crawford, Brandon Powell, Michelle R. |
author_sort | Talsma, Carl J. |
collection | PubMed |
description | This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events is important to reduce the cost of agricultural frost damage and traditional numerical weather forecasts are often inaccurate at the field-scale in complex terrain. In this paper, we developed machine learning (ML) algorithms for the prediction of such frost events near Alcalde, NM at the point-scale. ML algorithms investigated include deep neural network, convolution neural networks, and random forest models at lead-times of 6–48 h. Our results show promising accuracy (6-h prediction RMSE = 1.53–1.72°C) for use in frost and minimum temperature prediction applications. Seasonal differences in model predictions resulted in a slight negative bias during Spring and Summer months and a positive bias in Fall and Winter months. Additionally, we tested the model transferability by continuing training and testing using data from sensors at a nearby farm. We calculated the feature importance of the random forest models and were able to determine which parameters provided the models with the most useful information for predictions. We determined that soil temperature is a key parameter in longer term predictions (>24 h), while other temperature related parameters provide the majority of information for shorter term predictions. The model error compared favorable to previous ML based frost studies and outperformed the physically based High Resolution Rapid Refresh forecasting system making our ML-models attractive for deployment toward real-time monitoring of frost events and damage at commercial farming operations. |
format | Online Article Text |
id | pubmed-9878450 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-98784502023-01-27 Frost prediction using machine learning and deep neural network models Talsma, Carl J. Solander, Kurt C. Mudunuru, Maruti K. Crawford, Brandon Powell, Michelle R. Front Artif Intell Artificial Intelligence This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events is important to reduce the cost of agricultural frost damage and traditional numerical weather forecasts are often inaccurate at the field-scale in complex terrain. In this paper, we developed machine learning (ML) algorithms for the prediction of such frost events near Alcalde, NM at the point-scale. ML algorithms investigated include deep neural network, convolution neural networks, and random forest models at lead-times of 6–48 h. Our results show promising accuracy (6-h prediction RMSE = 1.53–1.72°C) for use in frost and minimum temperature prediction applications. Seasonal differences in model predictions resulted in a slight negative bias during Spring and Summer months and a positive bias in Fall and Winter months. Additionally, we tested the model transferability by continuing training and testing using data from sensors at a nearby farm. We calculated the feature importance of the random forest models and were able to determine which parameters provided the models with the most useful information for predictions. We determined that soil temperature is a key parameter in longer term predictions (>24 h), while other temperature related parameters provide the majority of information for shorter term predictions. The model error compared favorable to previous ML based frost studies and outperformed the physically based High Resolution Rapid Refresh forecasting system making our ML-models attractive for deployment toward real-time monitoring of frost events and damage at commercial farming operations. Frontiers Media S.A. 2023-01-12 /pmc/articles/PMC9878450/ /pubmed/36714205 http://dx.doi.org/10.3389/frai.2022.963781 Text en Copyright © 2023 Talsma, Solander, Mudunuru, Crawford and Powell. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Artificial Intelligence Talsma, Carl J. Solander, Kurt C. Mudunuru, Maruti K. Crawford, Brandon Powell, Michelle R. Frost prediction using machine learning and deep neural network models |
title | Frost prediction using machine learning and deep neural network models |
title_full | Frost prediction using machine learning and deep neural network models |
title_fullStr | Frost prediction using machine learning and deep neural network models |
title_full_unstemmed | Frost prediction using machine learning and deep neural network models |
title_short | Frost prediction using machine learning and deep neural network models |
title_sort | frost prediction using machine learning and deep neural network models |
topic | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9878450/ https://www.ncbi.nlm.nih.gov/pubmed/36714205 http://dx.doi.org/10.3389/frai.2022.963781 |
work_keys_str_mv | AT talsmacarlj frostpredictionusingmachinelearninganddeepneuralnetworkmodels AT solanderkurtc frostpredictionusingmachinelearninganddeepneuralnetworkmodels AT mudunurumarutik frostpredictionusingmachinelearninganddeepneuralnetworkmodels AT crawfordbrandon frostpredictionusingmachinelearninganddeepneuralnetworkmodels AT powellmicheller frostpredictionusingmachinelearninganddeepneuralnetworkmodels |