Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea
Pu-erh tea, Camellia sinensis is a traditional Chinese tea, one of the black teas, originally produced in China’s Yunnan Province, named after its origin and distribution center in Pu-erh, Yunnan. Yunnan Pu-erh tea is protected by geographical Indication and has unique quality characteristics. It is...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/11/1778 |
| _version_ | 1797468223198724096 |
|---|---|
| author | Xiaobo Cai Wenxia Yuan Xiaohui Liu Xinghua Wang Yaping Chen Xiujuan Deng Qi Wu Ke Han Zhiyong Cao Wendou Wu Baijuan Wang |
| author_facet | Xiaobo Cai Wenxia Yuan Xiaohui Liu Xinghua Wang Yaping Chen Xiujuan Deng Qi Wu Ke Han Zhiyong Cao Wendou Wu Baijuan Wang |
| author_sort | Xiaobo Cai |
| collection | DOAJ |
| description | Pu-erh tea, Camellia sinensis is a traditional Chinese tea, one of the black teas, originally produced in China’s Yunnan Province, named after its origin and distribution center in Pu-erh, Yunnan. Yunnan Pu-erh tea is protected by geographical Indication and has unique quality characteristics. It is made from Yunnan large-leaf sun-green tea with specific processing techniques. The quality formation of Pu-erh tea is closely related to the soil’s environmental conditions. In this paper, time-by-time data of the soil environment of tea plantations during the autumn tea harvesting period in Menghai County, Xishuangbanna, Yunnan Province, China, in 2021 were analyzed. Spearman’s correlation analysis was conducted between the inner components of Pu’er tea and the soil environmental factor. The analysis showed that three soil environmental indicators, soil temperature, soil moisture, and soil pH, were highly significantly correlated. The soil environmental quality evaluation method was proposed based on the selected soil environmental characteristics. Meanwhile, a deep learning model of Long Short Term Memory (LSTM) Network for the soil environmental quality of tea plantation was established according to the proposed method, and the soil environmental quality of tea was classified into four classes. In addition, the paper also compares the constructed models based on BP neural network and random forest to evaluate the coefficient of determination (R<sup>2</sup>), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the indicators for comparative analysis. This paper innovatively proposes to introduce the main inclusions of Pu’er tea into the classification and discrimination model of the soil environment in tea plantations, while using machine learning-related algorithms to classify and predict the categories of soil environmental quality, instead of relying solely on statistical data for analysis. This research work makes it possible to quickly and accurately determines the physiological status of tea leaves based on the establishment of a soil environment quality prediction model, which provides effective data for the intelligent management of tea plantations and has the advantage of rapid and low-cost assessment compared with the need to measure the intrinsic quality of Pu-erh tea after harvesting is completed. |
| first_indexed | 2024-03-09T19:04:26Z |
| format | Article |
| id | doaj.art-53f8e95cbb2f4241b4f7e209ee865a24 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-09T19:04:26Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-53f8e95cbb2f4241b4f7e209ee865a242023-11-24T04:43:05ZengMDPI AGForests1999-49072022-10-011311177810.3390/f13111778Deep Learning Model for Soil Environment Quality Classification of Pu-erh TeaXiaobo Cai0Wenxia Yuan1Xiaohui Liu2Xinghua Wang3Yaping Chen4Xiujuan Deng5Qi Wu6Ke Han7Zhiyong Cao8Wendou Wu9Baijuan Wang10Key Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Electrical and Mechanical, Kunming Metallurgy College, Kunming 650033, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaKey Laboratory of Intelligent Organic Tea Garden Construction in Universities of Yunnan Province, Yunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaPu-erh tea, Camellia sinensis is a traditional Chinese tea, one of the black teas, originally produced in China’s Yunnan Province, named after its origin and distribution center in Pu-erh, Yunnan. Yunnan Pu-erh tea is protected by geographical Indication and has unique quality characteristics. It is made from Yunnan large-leaf sun-green tea with specific processing techniques. The quality formation of Pu-erh tea is closely related to the soil’s environmental conditions. In this paper, time-by-time data of the soil environment of tea plantations during the autumn tea harvesting period in Menghai County, Xishuangbanna, Yunnan Province, China, in 2021 were analyzed. Spearman’s correlation analysis was conducted between the inner components of Pu’er tea and the soil environmental factor. The analysis showed that three soil environmental indicators, soil temperature, soil moisture, and soil pH, were highly significantly correlated. The soil environmental quality evaluation method was proposed based on the selected soil environmental characteristics. Meanwhile, a deep learning model of Long Short Term Memory (LSTM) Network for the soil environmental quality of tea plantation was established according to the proposed method, and the soil environmental quality of tea was classified into four classes. In addition, the paper also compares the constructed models based on BP neural network and random forest to evaluate the coefficient of determination (R<sup>2</sup>), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the indicators for comparative analysis. This paper innovatively proposes to introduce the main inclusions of Pu’er tea into the classification and discrimination model of the soil environment in tea plantations, while using machine learning-related algorithms to classify and predict the categories of soil environmental quality, instead of relying solely on statistical data for analysis. This research work makes it possible to quickly and accurately determines the physiological status of tea leaves based on the establishment of a soil environment quality prediction model, which provides effective data for the intelligent management of tea plantations and has the advantage of rapid and low-cost assessment compared with the need to measure the intrinsic quality of Pu-erh tea after harvesting is completed.https://www.mdpi.com/1999-4907/13/11/1778soil environmentdeep learninggrade classificationPu-erh tea |
| spellingShingle | Xiaobo Cai Wenxia Yuan Xiaohui Liu Xinghua Wang Yaping Chen Xiujuan Deng Qi Wu Ke Han Zhiyong Cao Wendou Wu Baijuan Wang Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea Forests soil environment deep learning grade classification Pu-erh tea |
| title | Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea |
| title_full | Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea |
| title_fullStr | Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea |
| title_full_unstemmed | Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea |
| title_short | Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea |
| title_sort | deep learning model for soil environment quality classification of pu erh tea |
| topic | soil environment deep learning grade classification Pu-erh tea |
| url | https://www.mdpi.com/1999-4907/13/11/1778 |
| work_keys_str_mv | AT xiaobocai deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT wenxiayuan deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT xiaohuiliu deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT xinghuawang deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT yapingchen deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT xiujuandeng deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT qiwu deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT kehan deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT zhiyongcao deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT wendouwu deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea AT baijuanwang deeplearningmodelforsoilenvironmentqualityclassificationofpuerhtea |