Machine learning versus crop growth models: an ally, not a rival
文献类型：期刊论文
| 作者 | Zhang, Ningyi1,5; Zhou, Xiaohan1,4; Kang, Mengzhen3 ; Hu, Bao-Gang2; Heuvelink, Ep1; Marcelis, Leo F. M.1
|
| 刊名 | AOB PLANTS
 |
| 出版日期 | 2023-02-01 |
| 卷号 | 15期号:2页码:7 |
| ISSN号 | 2041-2851 |
| 关键词 | Knowledge and data-driven modelling Machine learning Process-based models yield prediction |
| DOI | 10.1093/aobpla/plac061 |
| 通讯作者 | Zhang, Ningyi(ningyi.zhang@njau.edu.cn) ; Marcelis, Leo F. M.(leo.marcelis@wur.nl) |
| 英文摘要 | The rapid increases of the global population and climate change pose major challenges to a sustainable production of food to meet consumer demands. Process-based models (PBMs) have long been used in agricultural crop production for predicting yield and understanding the environmental regulation of plant physiological processes and its consequences for crop growth and development. In recent years, with the increasing use of sensor and communication technologies for data acquisition in agriculture, machine learning (ML) has become a popular tool in yield prediction (especially on a large scale) and phenotyping. Both PBMs and ML are frequently used in studies on major challenges in crop production and each has its own advantages and drawbacks. We propose to combine PBMs and ML given their intrinsic complementarity, to develop knowledge- and data-driven modelling (KDDM) with high prediction accuracy as well as good interpretability. Parallel, serial and modular structures are three main modes can be adopted to develop KDDM for agricultural applications. The KDDM approach helps to simplify model parameterization by making use of sensor data and improves the accuracy of yield prediction. Furthermore, the KDDM approach has great potential to expand the boundary of current crop models to allow upscaling towards a farm, regional or global level and downscaling to the gene-to-cell level. The KDDM approach is a promising way of combining simulation models in agriculture with the fast developments in data science while mechanisms of many genetic and physiological processes are still under investigation, especially at the nexus of increasing food production, mitigating climate change and achieving sustainability. We humans are at the nexus of increasing food production, mitigating climate change and achieving sustainable agriculture. Simulation models are useful tools for dealing with those challenges. Combining process-based models and machine learning to develop a knowledge- and data-driven modelling (KDDM) approach provides the opportunity of taking advantages of both modelling tools. Such a KDDM approach potentially increases the prediction accuracy of current modelling tools used in agriculture while keeping their interpretability at a good level. Parallel, serial and modular structures are three useful structures that can be adopted to develop a KDDM approach for agricultural applications. |
| WOS关键词 | IMPROVE ; KNOWLEDGE |
| WOS研究方向 | Plant Sciences ; Environmental Sciences & Ecology |
| 语种 | 英语 |
| 出版者 | OXFORD UNIV PRESS |
| WOS记录号 | WOS:000921945700001 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53552]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Zhang, Ningyi; Marcelis, Leo F. M. |
| 作者单位 | 1.Wageningen Univ, Dept Plant Sci, Hort & Prod Physiol, POB 16, NL-6700 AA Wageningen, Netherlands 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit CASIA NLPR, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Sate Key Lab Management & Control Complex Syst CAS, Beijing 100190, Peoples R China 4.Shanghai Lankuaikei Technol Dev Co Ltd, Shanghai 200120, Peoples R China 5.Nanjing Agr Univ, Coll Hort, Nanjing 210095, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Ningyi,Zhou, Xiaohan,Kang, Mengzhen,et al. Machine learning versus crop growth models: an ally, not a rival[J]. AOB PLANTS,2023,15(2):7. |
| APA | Zhang, Ningyi,Zhou, Xiaohan,Kang, Mengzhen,Hu, Bao-Gang,Heuvelink, Ep,&Marcelis, Leo F. M..(2023).Machine learning versus crop growth models: an ally, not a rival.AOB PLANTS,15(2),7. |
| MLA | Zhang, Ningyi,et al."Machine learning versus crop growth models: an ally, not a rival".AOB PLANTS 15.2(2023):7. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。