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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Frontiers in artificial intelligence Ročník 5; s. 963781
Hlavní autoři: Talsma, Carl J., Solander, Kurt C., Mudunuru, Maruti K., Crawford, Brandon, Powell, Michelle R.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Switzerland Frontiers Media S.A 12.01.2023
Témata:
Artificial Intelligence
earth sciences
frost damage
frost damage, machine learning, neural network, random forests, temperature prediction, weather models
machine learning
MATHEMATICS AND COMPUTING
neural networks
random forests
temperature prediction
frost damage
random forests
temperature prediction
machine learning
neural networks
ISSN:2624-8212, 2624-8212
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
AC05-76RL01830; 89233218CNA000001
New Mexico Small Business Assistance (NMSBA)
PNNL-SA-180159; LA-UR-20-26558
USDOE National Nuclear Security Administration (NNSA)
Reviewed by: Miltos Alamaniotis, University of Texas at San Antonio, United States; Thushara Gunda, Sandia National Laboratories (DOE), United States
Edited by: Hannah Kerner, University of Maryland, United States
This article was submitted to AI in Food, Agriculture and Water, a section of the journal Frontiers in Artificial Intelligence
ISSN:2624-8212
2624-8212
DOI:10.3389/frai.2022.963781