Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation

Advanced machine learning techniques have been used in remote sensing (RS) applications such as crop mapping and yield prediction, but remain under-utilized for tracking crop progress. In this study, we demonstrate the use of agronomic knowledge of crop growth drivers in a Long Short-Term Memory-bas...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	George Worrall, Anand Rangarajan, Jasmeet Judge
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	domain-guided machine learning remotely-sensed FPAR in-season crop growth estimation long short-term memory Science Q
Acceso en línea:	https://doaj.org/article/8537054293da40fd830ceb330f6817a0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8537054293da40fd830ceb330f6817a0
record_format	dspace
spelling	oai:doaj.org-article:8537054293da40fd830ceb330f6817a02021-11-25T18:54:40ZDomain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation10.3390/rs132246052072-4292https://doaj.org/article/8537054293da40fd830ceb330f6817a02021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4605https://doaj.org/toc/2072-4292Advanced machine learning techniques have been used in remote sensing (RS) applications such as crop mapping and yield prediction, but remain under-utilized for tracking crop progress. In this study, we demonstrate the use of agronomic knowledge of crop growth drivers in a Long Short-Term Memory-based, domain-guided neural network (DgNN) for in-season crop progress estimation. The DgNN uses a branched structure and attention to separate independent crop growth drivers and captures their varying importance throughout the growing season. The DgNN is implemented for corn, using RS data in Iowa, U.S., for the period 2003–2019, with United States Department of Agriculture (USDA) crop progress reports used as ground truth. State-wide DgNN performance shows significant improvement over sequential and dense-only NN structures, and a widely-used Hidden Markov Model method. The DgNN had a 4.0% higher Nash-Sutcliffe efficiency over all growth stages and 39% more weeks with highest cosine similarity than the next best NN during test years. The DgNN and Sequential NN were more robust during periods of abnormal crop progress, though estimating the Silking–Grainfill transition was difficult for all methods. Finally, Uniform Manifold Approximation and Projection visualizations of layer activations showed how LSTM-based NNs separate crop growth time-series differently from a dense-only structure. Results from this study exhibit both the viability of NNs in crop growth stage estimation (CGSE) and the benefits of using domain knowledge. The DgNN methodology presented here can be extended to provide near-real time CGSE of other crops.George WorrallAnand RangarajanJasmeet JudgeMDPI AGarticledomain-guided machine learningremotely-sensed FPARin-season crop growth estimationlong short-term memoryScienceQENRemote Sensing, Vol 13, Iss 4605, p 4605 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	domain-guided machine learning remotely-sensed FPAR in-season crop growth estimation long short-term memory Science Q
spellingShingle	domain-guided machine learning remotely-sensed FPAR in-season crop growth estimation long short-term memory Science Q George Worrall Anand Rangarajan Jasmeet Judge Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
description	Advanced machine learning techniques have been used in remote sensing (RS) applications such as crop mapping and yield prediction, but remain under-utilized for tracking crop progress. In this study, we demonstrate the use of agronomic knowledge of crop growth drivers in a Long Short-Term Memory-based, domain-guided neural network (DgNN) for in-season crop progress estimation. The DgNN uses a branched structure and attention to separate independent crop growth drivers and captures their varying importance throughout the growing season. The DgNN is implemented for corn, using RS data in Iowa, U.S., for the period 2003–2019, with United States Department of Agriculture (USDA) crop progress reports used as ground truth. State-wide DgNN performance shows significant improvement over sequential and dense-only NN structures, and a widely-used Hidden Markov Model method. The DgNN had a 4.0% higher Nash-Sutcliffe efficiency over all growth stages and 39% more weeks with highest cosine similarity than the next best NN during test years. The DgNN and Sequential NN were more robust during periods of abnormal crop progress, though estimating the Silking–Grainfill transition was difficult for all methods. Finally, Uniform Manifold Approximation and Projection visualizations of layer activations showed how LSTM-based NNs separate crop growth time-series differently from a dense-only structure. Results from this study exhibit both the viability of NNs in crop growth stage estimation (CGSE) and the benefits of using domain knowledge. The DgNN methodology presented here can be extended to provide near-real time CGSE of other crops.
format	article
author	George Worrall Anand Rangarajan Jasmeet Judge
author_facet	George Worrall Anand Rangarajan Jasmeet Judge
author_sort	George Worrall
title	Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
title_short	Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
title_full	Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
title_fullStr	Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
title_full_unstemmed	Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
title_sort	domain-guided machine learning for remotely sensed in-season crop growth estimation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8537054293da40fd830ceb330f6817a0
work_keys_str_mv	AT georgeworrall domainguidedmachinelearningforremotelysensedinseasoncropgrowthestimation AT anandrangarajan domainguidedmachinelearningforremotelysensedinseasoncropgrowthestimation AT jasmeetjudge domainguidedmachinelearningforremotelysensedinseasoncropgrowthestimation
_version_	1718410599545700352

Domain-Guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation

Ejemplares similares