CROP YIELD PREDICTION: AN OPERATIONAL APPROACH TO CROP YIELD MODELING ON FIELD AND SUBFIELD LEVEL WITH MACHINE LEARNING MODELS

被引：2

作者：

Helber, Patrick ^{[1
]}

Bischke, Benjamin ^{[1
]}

Habelitz, Peter ^{[1
]}

Sanchez, Cristhian ^{[2
,3
]}

Pathak, Deepak ^{[2
,3
]}

Miranda, Miro ^{[2
,3
]}

Najjar, Hiba ^{[2
,3
]}

Mena, Francisco ^{[2
,3
]}

Siddamsetty, Jayanth ^{[2
]}

Arenas, Diego ^{[2
]}

Vollmer, Michaela ^{[2
]}

Charfuelan, Marcela ^{[2
]}

Nuske, Marlon ^{[2
]}

Dengel, Andreas ^{[2
,3
]}

机构：

[1] Vis Impulse GmbH, Kaiserslautern, Germany

[2] German Res Ctr Artificial Intelligence DFKI, Kaiserslautern, Germany

[3] Univ Kaiserslautern Landau, Kaiserslautern, Germany

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

关键词：

Yield Estimation; Yield Forecasting;

D O I：

10.1109/IGARSS52108.2023.10283302

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

Accurate and reliable crop yield prediction is a complex task. The yield of a crop depends on a variety of factors whose accurate measurement and modeling is challenging. At the same time, reliable yield prediction is highly desirable for farmers to optimize crop production. In this paper, we introduce a modeling based on remote sensing data and Machine Learning models evaluated on a large-scale dataset to address the challenge of an operational crop yield estimation and forecasting on field and subfield level. With our approach, we aim towards a global yield modeling based on Machine Learning models which operates across crop types without the need for crop-specific modeling. We demonstrate that our approach learns to map in-field variability for all studied crop types. Overall, the predictions have an error (RRMSE) of around 15% and an R-2 value of 0.77 at field level.

引用

页码：2763 / 2766

页数：4

共 15 条

[1]

[Anonymous], 2009, PROG NAT SCI

[2] Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review [J].