Machine learning-based prediction of soil organic matter via smartphone
Color is an important property of soil that indicates soil composition and fertility. Soil organic matter (SOM) of darker color soils, which have rich humus and minerals, is higher than others such as red soils. The aim of this study is to construct models to predict SOM for a range of colors using...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | All Life |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/26895293.2024.2422109 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593496382373888 |
|---|---|
| author | Qingying Gao Yi Chen Hui Zhang Jingjing Chen Liang Wang |
| author_facet | Qingying Gao Yi Chen Hui Zhang Jingjing Chen Liang Wang |
| author_sort | Qingying Gao |
| collection | DOAJ |
| description | Color is an important property of soil that indicates soil composition and fertility. Soil organic matter (SOM) of darker color soils, which have rich humus and minerals, is higher than others such as red soils. The aim of this study is to construct models to predict SOM for a range of colors using a smartphone as an image-capturing device. Random forest of classification (RFC), random forest of logical regression (RFLR), convolutional neural network (CNN) and MobileNet models are compared, which is better for SOM prediction. Soil photos were collected by smartphone in a camera obscura with a steady light. After treatment by OpenCV, photos were separated by SOM content into five groups. The prediction accuracies of RFC, RFLR, CNN and MobileNet were 0.9743, 0.5614, 0.9600 and 0.7915, respectively. Based on these results, the RFC model for SOM has the best performance both in training and validation. The proposed combination of smartphone and machine learning-based prediction models provide a fast, economic, and robust approach to monitor, detect, and predict SOM contents in precision and intelligence agriculture. |
| format | Article |
| id | doaj-art-bded7197710e4e94bbf210b8d9b46c71 |
| institution | Kabale University |
| issn | 2689-5307 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | All Life |
| spelling | doaj-art-bded7197710e4e94bbf210b8d9b46c712025-01-20T14:38:00ZengTaylor & Francis GroupAll Life2689-53072024-12-01170110.1080/26895293.2024.24221092422109Machine learning-based prediction of soil organic matter via smartphoneQingying Gao0Yi Chen1Hui Zhang2Jingjing Chen3Liang Wang4Center for Analysis and Test, Science Technology and Vocational CollegeWenzhou PolytechnicCenter for Analysis and Test, Science Technology and Vocational CollegeCenter for Analysis and Test, Science Technology and Vocational CollegeCenter for Analysis and Test, Science Technology and Vocational CollegeColor is an important property of soil that indicates soil composition and fertility. Soil organic matter (SOM) of darker color soils, which have rich humus and minerals, is higher than others such as red soils. The aim of this study is to construct models to predict SOM for a range of colors using a smartphone as an image-capturing device. Random forest of classification (RFC), random forest of logical regression (RFLR), convolutional neural network (CNN) and MobileNet models are compared, which is better for SOM prediction. Soil photos were collected by smartphone in a camera obscura with a steady light. After treatment by OpenCV, photos were separated by SOM content into five groups. The prediction accuracies of RFC, RFLR, CNN and MobileNet were 0.9743, 0.5614, 0.9600 and 0.7915, respectively. Based on these results, the RFC model for SOM has the best performance both in training and validation. The proposed combination of smartphone and machine learning-based prediction models provide a fast, economic, and robust approach to monitor, detect, and predict SOM contents in precision and intelligence agriculture.http://dx.doi.org/10.1080/26895293.2024.2422109machine visionsoil organic mattermachine learning |
| spellingShingle | Qingying Gao Yi Chen Hui Zhang Jingjing Chen Liang Wang Machine learning-based prediction of soil organic matter via smartphone All Life machine vision soil organic matter machine learning |
| title | Machine learning-based prediction of soil organic matter via smartphone |
| title_full | Machine learning-based prediction of soil organic matter via smartphone |
| title_fullStr | Machine learning-based prediction of soil organic matter via smartphone |
| title_full_unstemmed | Machine learning-based prediction of soil organic matter via smartphone |
| title_short | Machine learning-based prediction of soil organic matter via smartphone |
| title_sort | machine learning based prediction of soil organic matter via smartphone |
| topic | machine vision soil organic matter machine learning |
| url | http://dx.doi.org/10.1080/26895293.2024.2422109 |
| work_keys_str_mv | AT qingyinggao machinelearningbasedpredictionofsoilorganicmatterviasmartphone AT yichen machinelearningbasedpredictionofsoilorganicmatterviasmartphone AT huizhang machinelearningbasedpredictionofsoilorganicmatterviasmartphone AT jingjingchen machinelearningbasedpredictionofsoilorganicmatterviasmartphone AT liangwang machinelearningbasedpredictionofsoilorganicmatterviasmartphone |