Assessment of Leaf Area and Biomass through AI-Enabled Deployment
Leaf area and biomass are important morphological parameters for in situ plant monitoring since a leaf is vital for perceiving and capturing the environmental light as well as represents the overall plant development. The traditional approach for leaf area and biomass measurements is destructive req...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Eng |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4117/4/3/116 |
| _version_ | 1797580319858098176 |
|---|---|
| author | Dmitrii Shadrin Alexander Menshchikov Artem Nikitin George Ovchinnikov Vera Volohina Sergey Nesteruk Mariia Pukalchik Maxim Fedorov Andrey Somov |
| author_facet | Dmitrii Shadrin Alexander Menshchikov Artem Nikitin George Ovchinnikov Vera Volohina Sergey Nesteruk Mariia Pukalchik Maxim Fedorov Andrey Somov |
| author_sort | Dmitrii Shadrin |
| collection | DOAJ |
| description | Leaf area and biomass are important morphological parameters for in situ plant monitoring since a leaf is vital for perceiving and capturing the environmental light as well as represents the overall plant development. The traditional approach for leaf area and biomass measurements is destructive requiring manual labor and may cause damages for the plants. In this work, we report on the AI-based approach for assessing and predicting the leaf area and plant biomass. The proposed approach is able to estimate and predict the overall plants biomass at the early stage of growth in a non-destructive way. For this reason we equip an industrial greenhouse for cucumbers growing with the commercial off-the-shelf environmental sensors and video cameras. The data from sensors are used to monitor the environmental conditions in the greenhouse while the top-down images are used for training Fully Convolutional Neural Networks (FCNN). The FCNN performs the segmentation task for leaf area calculation resulting in 82% accuracy. Application of trained FCNNs to the sequences of camera images allowed the reconstruction of per-plant leaf area and their growth-dynamics. Then we established the dependency between the average leaf area and biomass using the direct measurements of the biomass. This in turn allowed for reconstruction and prediction of the dynamics of biomass growth in the greenhouse using the image data with 10% average relative error for the 12 days prediction horizon. The actual deployment showed the high potential of the proposed data-driven approaches for plant growth dynamics assessment and prediction. Moreover, it closes the gap towards constructing fully closed autonomous greenhouses for harvests and plants biological safety. |
| first_indexed | 2024-03-10T22:49:18Z |
| format | Article |
| id | doaj.art-7b3c4ae04834429c979fed8877441e98 |
| institution | Directory Open Access Journal |
| issn | 2673-4117 |
| language | English |
| last_indexed | 2024-03-10T22:49:18Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Eng |
| spelling | doaj.art-7b3c4ae04834429c979fed8877441e982023-11-19T10:29:52ZengMDPI AGEng2673-41172023-07-01432055207410.3390/eng4030116Assessment of Leaf Area and Biomass through AI-Enabled DeploymentDmitrii Shadrin0Alexander Menshchikov1Artem Nikitin2George Ovchinnikov3Vera Volohina4Sergey Nesteruk5Mariia Pukalchik6Maxim Fedorov7Andrey Somov8Skolkovo Institute of Science and Technology, 121205 Moscow, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaMichurinsk State Agrarian University, 393760 Michurinsk, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaSberbank of Russia, 117312 Moscow, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaSkolkovo Institute of Science and Technology, 121205 Moscow, RussiaLeaf area and biomass are important morphological parameters for in situ plant monitoring since a leaf is vital for perceiving and capturing the environmental light as well as represents the overall plant development. The traditional approach for leaf area and biomass measurements is destructive requiring manual labor and may cause damages for the plants. In this work, we report on the AI-based approach for assessing and predicting the leaf area and plant biomass. The proposed approach is able to estimate and predict the overall plants biomass at the early stage of growth in a non-destructive way. For this reason we equip an industrial greenhouse for cucumbers growing with the commercial off-the-shelf environmental sensors and video cameras. The data from sensors are used to monitor the environmental conditions in the greenhouse while the top-down images are used for training Fully Convolutional Neural Networks (FCNN). The FCNN performs the segmentation task for leaf area calculation resulting in 82% accuracy. Application of trained FCNNs to the sequences of camera images allowed the reconstruction of per-plant leaf area and their growth-dynamics. Then we established the dependency between the average leaf area and biomass using the direct measurements of the biomass. This in turn allowed for reconstruction and prediction of the dynamics of biomass growth in the greenhouse using the image data with 10% average relative error for the 12 days prediction horizon. The actual deployment showed the high potential of the proposed data-driven approaches for plant growth dynamics assessment and prediction. Moreover, it closes the gap towards constructing fully closed autonomous greenhouses for harvests and plants biological safety.https://www.mdpi.com/2673-4117/4/3/116artificial intelligencedeploymentimage analysisenvironmental sensingneural networkssensor network |
| spellingShingle | Dmitrii Shadrin Alexander Menshchikov Artem Nikitin George Ovchinnikov Vera Volohina Sergey Nesteruk Mariia Pukalchik Maxim Fedorov Andrey Somov Assessment of Leaf Area and Biomass through AI-Enabled Deployment Eng artificial intelligence deployment image analysis environmental sensing neural networks sensor network |
| title | Assessment of Leaf Area and Biomass through AI-Enabled Deployment |
| title_full | Assessment of Leaf Area and Biomass through AI-Enabled Deployment |
| title_fullStr | Assessment of Leaf Area and Biomass through AI-Enabled Deployment |
| title_full_unstemmed | Assessment of Leaf Area and Biomass through AI-Enabled Deployment |
| title_short | Assessment of Leaf Area and Biomass through AI-Enabled Deployment |
| title_sort | assessment of leaf area and biomass through ai enabled deployment |
| topic | artificial intelligence deployment image analysis environmental sensing neural networks sensor network |
| url | https://www.mdpi.com/2673-4117/4/3/116 |
| work_keys_str_mv | AT dmitriishadrin assessmentofleafareaandbiomassthroughaienableddeployment AT alexandermenshchikov assessmentofleafareaandbiomassthroughaienableddeployment AT artemnikitin assessmentofleafareaandbiomassthroughaienableddeployment AT georgeovchinnikov assessmentofleafareaandbiomassthroughaienableddeployment AT veravolohina assessmentofleafareaandbiomassthroughaienableddeployment AT sergeynesteruk assessmentofleafareaandbiomassthroughaienableddeployment AT mariiapukalchik assessmentofleafareaandbiomassthroughaienableddeployment AT maximfedorov assessmentofleafareaandbiomassthroughaienableddeployment AT andreysomov assessmentofleafareaandbiomassthroughaienableddeployment |