Frost Prediction for Vineyard Using Machine Learning

Tamura, Yosuke; Ding, Liya; Noborio, Kosuke; Shibuya, Kazuo

doi:10.1109/scisisis50064.2020.9322770

Cited by 4 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because these other parameters were not collected at Freshies Farm, ML models at longer lead times were still reliant exclusively on temperature and thus exhibited less robust model performance. Previous ML studies have also reported difficulty in predicting frost at longer intervals (Tamura et al, 2020) and the addition of soil temperature shows promise for model improvement over these prediction windows.…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies where ML was employed to predict frost have yielded positive results in complex terrain (Ghielmi and Eccel, 2006 ; Eccel et al, 2007 ), and determined how integration of data from nearby weather station data may yield improved model predictions (Diedrichs et al, 2018 ). However, many ML frost prediction studies have either focused on classification of frost events (Möller-Acuña et al, 2017 ; Tamura et al, 2020 ; Noh et al, 2021 ) which, depending on the stage of bud development, may not be the most useful for characterizing actual crop mortality. For example, although the occurrence of frost may be enough to kill crops that are in the latter stages of bud development where flowers have started to form, temperatures lower than freezing are needed to destroy crops in earlier bud stages (e.g., bud swelling) (Salazar-Gutiérrez et al, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

“…Another missing aspect from previous studies is the use of prediction windows from both shorter (< 8 h) and longer (24–48 h) lead times to accommodate appropriate preparations for frost mitigation. Often, a single lead time is reported (Diedrichs et al, 2018 ) or model performance is significantly reduced at longer lead-times (Tamura et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Frost prediction using machine learning and deep neural network models

Talsma

Solander²,

Mudunuru³

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Frost prediction using machine learning and deep neural network models

Talsma

Solander²,

Mudunuru³

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Tamura et al [14] compared the SVM results using the simple moving average and exponential moving average as the past values of the temperature and vapor pressure variables. Models using exponential moving averages perform a few percentage points better than models using simple moving averages in terms of the F1-score (the harmonic mean of the precision or recall) measurements.…”

Section: Introductionmentioning

confidence: 99%

Frost Forecasting considering Geographical Characteristics

Kim

2022

Advances in Meteorology

View full text Add to dashboard Cite

Regional accuracy was examined using extreme gradient boosting (XGBoost) to improve frost prediction accuracy, and accuracy differences by region were found. When the points were divided into two groups with weather variables, Group 1 had a coastal climate with a high minimum temperature, humidity, and wind speed and Group 2 exhibited relatively inland climate characteristics. We calculated the accuracy in the two groups and found that the precision and recall scores in coastal areas (Group 1) were significantly lower than those in the inland areas (Group 2). Geographic elements (distance from the nearest coast and height) were added as variables to improve accuracy. In addition, considering the continuity of frost occurrence, the method of reflecting the frost occurrence of the previous day as a variable and the synthetic minority oversampling technique (SMOTE) pretreatment were used to increase the learning ability.

show abstract