A Study of Forest Phenology Prediction Based on GRU Models
Investigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishing gradients. In contrast, the Gated Recurrent Unit...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/8/4898 |
| _version_ | 1797606537880928256 |
|---|---|
| author | Peng Guan Lichen Zhu Yili Zheng |
| author_facet | Peng Guan Lichen Zhu Yili Zheng |
| author_sort | Peng Guan |
| collection | DOAJ |
| description | Investigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishing gradients. In contrast, the Gated Recurrent Unit (GRU) can effectively address the problem of vanishing gradients and allow the neural network to capture longer-range dependencies. In this study, an optical camera was used as experimental equipment to obtain forest images. The absolute greenness index (GEI) data of the region of interest (ROI) in the images were calculated to fit the seasonal variation curve of forest phenology. The GRU neural network model was introduced to train and analyze the GEI data, and the performance of the GRU neural network was evaluated using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) methods. Finally, the model was used to predict the trend of GEI data for the next 60 days. The results showed that: (1) In terms of training and predicting forest phenology, the GRU model was validated using histograms and autocorrelation graphs, which indicated that the distribution of predicted data was consistent with the trend of actual data, the GRU model data was feasible, and the model was stable. (2) The MSE values of the GRU model at rain-fed-CK (preset point 1), sufficient drip irrigation-DIFI (preset point 3), and sufficient furrow irrigation-BIFI (preset point 5) were 9.055 × 10<sup>−5</sup>, 12.91 × 10<sup>−5</sup>, and 8.241 × 10<sup>−5</sup>, respectively. The RMSE values were 9.516 × 10<sup>−3</sup>, 11.36 × 10<sup>−3</sup>, and 7.313 × 10<sup>−3</sup>, respectively. The MAE values were 7.174 × 10<sup>−3</sup>, 8.241 × 10<sup>−3</sup>, and 5.351 × 10<sup>−3</sup>, respectively. These results indicate that the overall performance of the GRU model was good. (3) The predicted GEI data for the next 60 days showed a trend consistent with actual changes in GEI data, as demonstrated by the GRU model. The GRU model has become the preferred method for phenological prediction due to its simple internal structure and relatively short training time. Results show that the GRU model can achieve forest phenological change prediction and can reveal in-depth insights into future forest growth and climate change, providing a theoretical basis for the application of forest phenological prediction. |
| first_indexed | 2024-03-11T05:16:36Z |
| format | Article |
| id | doaj.art-109bb8bc16d149eca46780cf6f88b2a2 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:16:36Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-109bb8bc16d149eca46780cf6f88b2a22023-11-17T18:10:52ZengMDPI AGApplied Sciences2076-34172023-04-01138489810.3390/app13084898A Study of Forest Phenology Prediction Based on GRU ModelsPeng Guan0Lichen Zhu1Yili Zheng2School of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaInvestigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishing gradients. In contrast, the Gated Recurrent Unit (GRU) can effectively address the problem of vanishing gradients and allow the neural network to capture longer-range dependencies. In this study, an optical camera was used as experimental equipment to obtain forest images. The absolute greenness index (GEI) data of the region of interest (ROI) in the images were calculated to fit the seasonal variation curve of forest phenology. The GRU neural network model was introduced to train and analyze the GEI data, and the performance of the GRU neural network was evaluated using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) methods. Finally, the model was used to predict the trend of GEI data for the next 60 days. The results showed that: (1) In terms of training and predicting forest phenology, the GRU model was validated using histograms and autocorrelation graphs, which indicated that the distribution of predicted data was consistent with the trend of actual data, the GRU model data was feasible, and the model was stable. (2) The MSE values of the GRU model at rain-fed-CK (preset point 1), sufficient drip irrigation-DIFI (preset point 3), and sufficient furrow irrigation-BIFI (preset point 5) were 9.055 × 10<sup>−5</sup>, 12.91 × 10<sup>−5</sup>, and 8.241 × 10<sup>−5</sup>, respectively. The RMSE values were 9.516 × 10<sup>−3</sup>, 11.36 × 10<sup>−3</sup>, and 7.313 × 10<sup>−3</sup>, respectively. The MAE values were 7.174 × 10<sup>−3</sup>, 8.241 × 10<sup>−3</sup>, and 5.351 × 10<sup>−3</sup>, respectively. These results indicate that the overall performance of the GRU model was good. (3) The predicted GEI data for the next 60 days showed a trend consistent with actual changes in GEI data, as demonstrated by the GRU model. The GRU model has become the preferred method for phenological prediction due to its simple internal structure and relatively short training time. Results show that the GRU model can achieve forest phenological change prediction and can reveal in-depth insights into future forest growth and climate change, providing a theoretical basis for the application of forest phenological prediction.https://www.mdpi.com/2076-3417/13/8/4898green excess indexGated Recurrent Unit modelpredictionforest phenology |
| spellingShingle | Peng Guan Lichen Zhu Yili Zheng A Study of Forest Phenology Prediction Based on GRU Models Applied Sciences green excess index Gated Recurrent Unit model prediction forest phenology |
| title | A Study of Forest Phenology Prediction Based on GRU Models |
| title_full | A Study of Forest Phenology Prediction Based on GRU Models |
| title_fullStr | A Study of Forest Phenology Prediction Based on GRU Models |
| title_full_unstemmed | A Study of Forest Phenology Prediction Based on GRU Models |
| title_short | A Study of Forest Phenology Prediction Based on GRU Models |
| title_sort | study of forest phenology prediction based on gru models |
| topic | green excess index Gated Recurrent Unit model prediction forest phenology |
| url | https://www.mdpi.com/2076-3417/13/8/4898 |
| work_keys_str_mv | AT pengguan astudyofforestphenologypredictionbasedongrumodels AT lichenzhu astudyofforestphenologypredictionbasedongrumodels AT yilizheng astudyofforestphenologypredictionbasedongrumodels AT pengguan studyofforestphenologypredictionbasedongrumodels AT lichenzhu studyofforestphenologypredictionbasedongrumodels AT yilizheng studyofforestphenologypredictionbasedongrumodels |