TY - JOUR
T1 - Maize grain and silage yield prediction of commercial fields using high-resolution UAS imagery
AU - Sunoj, S.
AU - Yeh, Benjamin
AU - Marcaida, Manuel
AU - Longchamps, Louis
AU - van Aardt, Jan
AU - Ketterings, Quirine M.
N1 - Funding Information:
The authors greatly appreciate the funding agencies for funding this project. This work was supported in part by Federal Formula Funds and through grants from the New York Farm Viability Institute (NYFVI) , the New York State Department of Environmental Conservation (NYSDEC) , and New York State Department of Agriculture and Markets (NYSAGM) . The authors would like to thank the farmers who shared their yield monitor data with us and allowed us to collect weekly UAS imagery. We would also like to thank Greg Godwin, former Research Support Specialist with the Nutrient Management Spear Program, Cornell University, Ithaca, NY, for doing weekly UAS flights on all eight fields in this study.
Funding Information:
The authors greatly appreciate the funding agencies for funding this project. This work was supported in part by Federal Formula Funds and through grants from the New York Farm Viability Institute (NYFVI), the New York State Department of Environmental Conservation (NYSDEC), and New York State Department of Agriculture and Markets (NYSAGM). The authors would like to thank the farmers who shared their yield monitor data with us and allowed us to collect weekly UAS imagery. We would also like to thank Greg Godwin, former Research Support Specialist with the Nutrient Management Spear Program, Cornell University, Ithaca, NY, for doing weekly UAS flights on all eight fields in this study.
Publisher Copyright:
© 2023 IAgrE
PY - 2023/11
Y1 - 2023/11
N2 - The aim was to evaluate if maize (Zea mays L.) grain and silage yield can be estimated from unmanned aerial systems (UAS) imagery. A fixed-wing UAS was used to collect imagery throughout the growing season (emergence to reproductive growth stages) at eight commercial fields, each implemented with a nitrogen-rich (NRich) strip. Exponential regression models were fitted between yield and seven vegetation indices (VIs) from NRich strip, whilst two machine learning (ML) regression models (random forest [RF] and support vector regression [SVR]) were fitted with VIs, elevation, and landform layers. The results showed that the normalised difference vegetation index (NDVI) was the most reliable indicator for yield using exponential models when the images were collected at late vegetative stages before tasseling for silage and late reproductive stage before senescence for grain. The exponential models performed better with NRich strip than those derived with the statistical reference strips (SRS) for fields without NRich strips, but the differences were minimal when sensed at a vegetative stage before tasselling. The Boruta algorithm identified elevation, landform, and three VIs as the top five important features for yield estimation. Using these five features, the RF model produced a lower error and was faster to train than the SVR. The ML models outperformed the exponential models with SRS but underperformed compared to the models with NRich strip. It was concluded that if a field does not have an NRich strip, using RF models with additional data layers can provide reliable yield estimations for maize grain and silage.
AB - The aim was to evaluate if maize (Zea mays L.) grain and silage yield can be estimated from unmanned aerial systems (UAS) imagery. A fixed-wing UAS was used to collect imagery throughout the growing season (emergence to reproductive growth stages) at eight commercial fields, each implemented with a nitrogen-rich (NRich) strip. Exponential regression models were fitted between yield and seven vegetation indices (VIs) from NRich strip, whilst two machine learning (ML) regression models (random forest [RF] and support vector regression [SVR]) were fitted with VIs, elevation, and landform layers. The results showed that the normalised difference vegetation index (NDVI) was the most reliable indicator for yield using exponential models when the images were collected at late vegetative stages before tasseling for silage and late reproductive stage before senescence for grain. The exponential models performed better with NRich strip than those derived with the statistical reference strips (SRS) for fields without NRich strips, but the differences were minimal when sensed at a vegetative stage before tasselling. The Boruta algorithm identified elevation, landform, and three VIs as the top five important features for yield estimation. Using these five features, the RF model produced a lower error and was faster to train than the SVR. The ML models outperformed the exponential models with SRS but underperformed compared to the models with NRich strip. It was concluded that if a field does not have an NRich strip, using RF models with additional data layers can provide reliable yield estimations for maize grain and silage.
KW - Machine learning
KW - Maize
KW - Precision agriculture
KW - Remote sensing
KW - Unmanned aerial system
KW - Yield prediction
UR - http://www.scopus.com/inward/record.url?scp=85173604530&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85173604530&partnerID=8YFLogxK
U2 - 10.1016/j.biosystemseng.2023.09.010
DO - 10.1016/j.biosystemseng.2023.09.010
M3 - Article
AN - SCOPUS:85173604530
SN - 1537-5110
VL - 235
SP - 137
EP - 149
JO - Biosystems Engineering
JF - Biosystems Engineering
ER -