Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification
For farmers, policymakers, and government agencies, it is critical to accurately define agricultural crop phenology and its spatial-temporal variability. At the moment, two approaches are utilized to report crop phenology. On one hand, land surface phenology provides information about the overall tr...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/3/469 |
_version_ | 1797485179545059328 |
---|---|
author | Luciana Nieto Rasmus Houborg Ariel Zajdband Arin Jumpasut P. V. Vara Prasad Brad J. S. C. Olson Ignacio A. Ciampitti |
author_facet | Luciana Nieto Rasmus Houborg Ariel Zajdband Arin Jumpasut P. V. Vara Prasad Brad J. S. C. Olson Ignacio A. Ciampitti |
author_sort | Luciana Nieto |
collection | DOAJ |
description | For farmers, policymakers, and government agencies, it is critical to accurately define agricultural crop phenology and its spatial-temporal variability. At the moment, two approaches are utilized to report crop phenology. On one hand, land surface phenology provides information about the overall trend, whereas weekly reports from USDA-NASS provide information about the development of particular crops at the regional level. High-cadence earth observations might help to improve the accuracy of these estimations and bring more precise crop phenology classifications closer to what farmers demand. The second component of the proposed solution requires the use of robust classifiers (e.g., random forest, RF) capable of successfully managing large data sets. To evaluate this solution, this study compared the output of a RF classifier model using weather, two different satellite sources (Planet Fusion; PF and Sentinel-2; S-2), and ground truth data to improve maize (<i>Zea mays</i> L.) crop phenology classification using two regions of Kansas (Southwest and Central) as a testbed during the 2017 growing season. Our findings suggests that high temporal resolution (PF) data can significantly improve crop classification metrics (f1-score = 0.94) relative to S-2 (f1-score = 0.86). Additionally, a decline in the f1-score between 0.74 and 0.60 was obtained when we assessed the ability of S-2 to extend the temporal forecast for crop phenology. This research highlights the critical nature of very high temporal resolution (daily) earth observation data for crop monitoring and decision making in agriculture. |
first_indexed | 2024-03-09T23:15:05Z |
format | Article |
id | doaj.art-cc07a10d16cd44fb92a5b21b9e29d654 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T23:15:05Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-cc07a10d16cd44fb92a5b21b9e29d6542023-11-23T17:38:11ZengMDPI AGRemote Sensing2072-42922022-01-0114346910.3390/rs14030469Impact of High-Cadence Earth Observation in Maize Crop Phenology ClassificationLuciana Nieto0Rasmus Houborg1Ariel Zajdband2Arin Jumpasut3P. V. Vara Prasad4Brad J. S. C. Olson5Ignacio A. Ciampitti6Department of Agronomy, Kansas State University, 1712 Claflin Road, Manhattan, KS 66506, USAPlanet Labs Inc., San Francisco, CA 94107, USAPlanet Labs Inc., San Francisco, CA 94107, USAPlanet Labs Inc., San Francisco, CA 94107, USADepartment of Agronomy, Kansas State University, 1712 Claflin Road, Manhattan, KS 66506, USADepartment of Biology, Kansas State University, Chalmers Hall, 1711 Claflin Road, Manhattan, KS 66506, USADepartment of Agronomy, Kansas State University, 1712 Claflin Road, Manhattan, KS 66506, USAFor farmers, policymakers, and government agencies, it is critical to accurately define agricultural crop phenology and its spatial-temporal variability. At the moment, two approaches are utilized to report crop phenology. On one hand, land surface phenology provides information about the overall trend, whereas weekly reports from USDA-NASS provide information about the development of particular crops at the regional level. High-cadence earth observations might help to improve the accuracy of these estimations and bring more precise crop phenology classifications closer to what farmers demand. The second component of the proposed solution requires the use of robust classifiers (e.g., random forest, RF) capable of successfully managing large data sets. To evaluate this solution, this study compared the output of a RF classifier model using weather, two different satellite sources (Planet Fusion; PF and Sentinel-2; S-2), and ground truth data to improve maize (<i>Zea mays</i> L.) crop phenology classification using two regions of Kansas (Southwest and Central) as a testbed during the 2017 growing season. Our findings suggests that high temporal resolution (PF) data can significantly improve crop classification metrics (f1-score = 0.94) relative to S-2 (f1-score = 0.86). Additionally, a decline in the f1-score between 0.74 and 0.60 was obtained when we assessed the ability of S-2 to extend the temporal forecast for crop phenology. This research highlights the critical nature of very high temporal resolution (daily) earth observation data for crop monitoring and decision making in agriculture.https://www.mdpi.com/2072-4292/14/3/469agriculturePlanet FusionSentinel-2random forest classifier |
spellingShingle | Luciana Nieto Rasmus Houborg Ariel Zajdband Arin Jumpasut P. V. Vara Prasad Brad J. S. C. Olson Ignacio A. Ciampitti Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification Remote Sensing agriculture Planet Fusion Sentinel-2 random forest classifier |
title | Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification |
title_full | Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification |
title_fullStr | Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification |
title_full_unstemmed | Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification |
title_short | Impact of High-Cadence Earth Observation in Maize Crop Phenology Classification |
title_sort | impact of high cadence earth observation in maize crop phenology classification |
topic | agriculture Planet Fusion Sentinel-2 random forest classifier |
url | https://www.mdpi.com/2072-4292/14/3/469 |
work_keys_str_mv | AT luciananieto impactofhighcadenceearthobservationinmaizecropphenologyclassification AT rasmushouborg impactofhighcadenceearthobservationinmaizecropphenologyclassification AT arielzajdband impactofhighcadenceearthobservationinmaizecropphenologyclassification AT arinjumpasut impactofhighcadenceearthobservationinmaizecropphenologyclassification AT pvvaraprasad impactofhighcadenceearthobservationinmaizecropphenologyclassification AT bradjscolson impactofhighcadenceearthobservationinmaizecropphenologyclassification AT ignacioaciampitti impactofhighcadenceearthobservationinmaizecropphenologyclassification |