Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle
Accurate prediction of sweet potato yield is crucial for effective crop management. This study investigates the use of vegetation indices (VIs) extracted from multispectral images acquired by a small unmanned aerial vehicle (UAV) throughout the growing season, along with in situ-measured plant physi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/4/420 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722556317171712 |
|---|---|
| author | Kriti Singh Yanbo Huang Wyatt Young Lorin Harvey Mark Hall Xin Zhang Edgar Lobaton Johnie Jenkins Mark Shankle |
| author_facet | Kriti Singh Yanbo Huang Wyatt Young Lorin Harvey Mark Hall Xin Zhang Edgar Lobaton Johnie Jenkins Mark Shankle |
| author_sort | Kriti Singh |
| collection | DOAJ |
| description | Accurate prediction of sweet potato yield is crucial for effective crop management. This study investigates the use of vegetation indices (VIs) extracted from multispectral images acquired by a small unmanned aerial vehicle (UAV) throughout the growing season, along with in situ-measured plant physiological parameters, to predict sweet potato yield. The data acquisition process through UAV field imaging is discussed in detail along with the extraction process for the multispectral bands that we use as features. The experiment is designed with a combination of different nitrogen application rates and cover crop treatments. The dependence of VIs and crop physiological parameters, such as leaf chlorophyll content, plant biomass, vine length, and leaf nitrogen content, on yield is evaluated through feature selection methods and model performance. Classical machine learning (ML) approaches and tree-based algorithms, like XGBoost and Random Forest, are implemented. Additionally, a soft-voting ML model ensemble approach is employed to improve performance of yield prediction. Individual models are trained and tested for different cover crop and nitrogen treatments to capture the relationships between the treatments and the target yield variable. The performance of the ML algorithms is evaluated using various popular model performance metrics like R<sup>2</sup>, RMSE, and MAE. Through modelling the data for cover crops and nitrogen treatment rates using individual models, the relationships and effects of different treatments on yield are explored. Important VIs useful for the study are identified through feature selection and model performance evaluation. |
| format | Article |
| id | doaj-art-c7c428114dca4bc8be06a30b481a1c7c |
| institution | DOAJ |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-c7c428114dca4bc8be06a30b481a1c7c2025-08-20T03:11:19ZengMDPI AGAgriculture2077-04722025-02-0115442010.3390/agriculture15040420Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial VehicleKriti Singh0Yanbo Huang1Wyatt Young2Lorin Harvey3Mark Hall4Xin Zhang5Edgar Lobaton6Johnie Jenkins7Mark Shankle8Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC 27606, USAUSDA-ARS Genetics and Sustainable Agriculture Research Unit, Mississippi State, MS 39762, USAUSDA-ARS Genetics and Sustainable Agriculture Research Unit, Mississippi State, MS 39762, USAPontotoc Ridge-Flatwoods Branch Experiment Station, Mississippi State University, Pontotoc, MS 38863, USAPontotoc Ridge-Flatwoods Branch Experiment Station, Mississippi State University, Pontotoc, MS 38863, USADepartment of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS 39762, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC 27606, USAUSDA-ARS Genetics and Sustainable Agriculture Research Unit, Mississippi State, MS 39762, USAPontotoc Ridge-Flatwoods Branch Experiment Station, Mississippi State University, Pontotoc, MS 38863, USAAccurate prediction of sweet potato yield is crucial for effective crop management. This study investigates the use of vegetation indices (VIs) extracted from multispectral images acquired by a small unmanned aerial vehicle (UAV) throughout the growing season, along with in situ-measured plant physiological parameters, to predict sweet potato yield. The data acquisition process through UAV field imaging is discussed in detail along with the extraction process for the multispectral bands that we use as features. The experiment is designed with a combination of different nitrogen application rates and cover crop treatments. The dependence of VIs and crop physiological parameters, such as leaf chlorophyll content, plant biomass, vine length, and leaf nitrogen content, on yield is evaluated through feature selection methods and model performance. Classical machine learning (ML) approaches and tree-based algorithms, like XGBoost and Random Forest, are implemented. Additionally, a soft-voting ML model ensemble approach is employed to improve performance of yield prediction. Individual models are trained and tested for different cover crop and nitrogen treatments to capture the relationships between the treatments and the target yield variable. The performance of the ML algorithms is evaluated using various popular model performance metrics like R<sup>2</sup>, RMSE, and MAE. Through modelling the data for cover crops and nitrogen treatment rates using individual models, the relationships and effects of different treatments on yield are explored. Important VIs useful for the study are identified through feature selection and model performance evaluation.https://www.mdpi.com/2077-0472/15/4/420sweet potatoyieldremote sensingunmanned aerial vehiclemachine learning |
| spellingShingle | Kriti Singh Yanbo Huang Wyatt Young Lorin Harvey Mark Hall Xin Zhang Edgar Lobaton Johnie Jenkins Mark Shankle Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle Agriculture sweet potato yield remote sensing unmanned aerial vehicle machine learning |
| title | Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle |
| title_full | Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle |
| title_fullStr | Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle |
| title_full_unstemmed | Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle |
| title_short | Sweet Potato Yield Prediction Using Machine Learning Based on Multispectral Images Acquired from a Small Unmanned Aerial Vehicle |
| title_sort | sweet potato yield prediction using machine learning based on multispectral images acquired from a small unmanned aerial vehicle |
| topic | sweet potato yield remote sensing unmanned aerial vehicle machine learning |
| url | https://www.mdpi.com/2077-0472/15/4/420 |
| work_keys_str_mv | AT kritisingh sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT yanbohuang sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT wyattyoung sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT lorinharvey sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT markhall sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT xinzhang sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT edgarlobaton sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT johniejenkins sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle AT markshankle sweetpotatoyieldpredictionusingmachinelearningbasedonmultispectralimagesacquiredfromasmallunmannedaerialvehicle |