CaltechAUTHORS
  A Caltech Library Service

Assessing the benefit of satellite-based Solar-Induced Chlorophyll Fluorescence in crop yield prediction

Peng, Bin and Guan, Kaiyu and Zhou, Wang and Jiang, Chongya and Frankenberg, Christian and Sun, Ying and He, Liyin and Köhler, Philipp (2020) Assessing the benefit of satellite-based Solar-Induced Chlorophyll Fluorescence in crop yield prediction. International Journal of Applied Earth Observation and Geoinformation, 90 . Art. No. 102126. ISSN 0303-2434. https://resolver.caltech.edu/CaltechAUTHORS:20200422-085520650

[img] PDF - Published Version
Creative Commons Attribution.

15Mb
[img] Archive (ZIP) - Supplemental Material
See Usage Policy.

568b

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200422-085520650

Abstract

Large-scale crop yield prediction is critical for early warning of food insecurity, agricultural supply chain management, and economic market. Satellite-based Solar-Induced Chlorophyll Fluorescence (SIF) products have revealed hot spots of photosynthesis over global croplands, such as in the U.S. Midwest. However, to what extent these satellite-based SIF products can enhance the performance of crop yield prediction when benchmarking against other existing satellite data remains unclear. Here we assessed the benefits of using three satellite-based SIF products in yield prediction for maize and soybean in the U.S. Midwest: gap-filled SIF from Orbiting Carbon Observatory 2 (OCO-2), new SIF retrievals from the TROPOspheric Monitoring Instrument (TROPOMI), and the coarse-resolution SIF retrievals from the Global Ozone Monitoring Experiment-2 (GOME-2). The yield prediction performances of using SIF data were benchmarked with those using satellite-based vegetation indices (VIs), including normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and near-infrared reflectance of vegetation (NIRv), and land surface temperature (LST). Five machine-learning algorithms were used to build yield prediction models with both remote-sensing-only and climate-remote-sensing-combined variables. We found that high-resolution SIF products from OCO-2 and TROPOMI outperformed coarse-resolution GOME-2 SIF product in crop yield prediction. Using high-resolution SIF products gave the best forward predictions for both maize and soybean yields in 2018, indicating the great potential of using satellite-based high-resolution SIF products for crop yield prediction. However, using currently available high-resolution SIF products did not guarantee consistently better yield prediction performances than using other satellite-based remote sensing variables in all the evaluated cases. The relative performances of using different remote sensing variables in yield prediction depended on crop types (maize or soybean), out-of-sample testing methods (five-fold-cross-validation or forward), and record length of training data. We also found that using NIRv could generally lead to better yield prediction performance than using NDVI, EVI, or LST, and using NIRv could achieve similar or even better yield prediction performance than using OCO-2 or TROPOMI SIF products. We concluded that satellite-based SIF products could be beneficial in crop yield prediction with more high-resolution and good-quality SIF products accumulated in the future.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1016/j.jag.2020.102126DOIArticle
ORCID:
AuthorORCID
Peng, Bin0000-0002-7284-3010
Jiang, Chongya0000-0002-1660-7320
Frankenberg, Christian0000-0002-0546-5857
Sun, Ying0000-0002-9819-1241
He, Liyin0000-0003-4427-1438
Köhler, Philipp0000-0002-7820-1318
Additional Information:© 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/). Received 4 December 2019, Revised 8 March 2020, Accepted 7 April 2020, Available online 22 April 2020. B.P., K.G., W.Z., and C.J. acknowledged the support from following NASA programs: New Investigator, Carbon Monitoring System, Carbon Cycle Science, and Harvest Program. K.G. also acknowledged support from NSF CAREER Award. All the data used in this study are publically available. County-level Maize and soybean yield and acreage survey data are available from USDA NASS through https://quickstats.nass.usda.gov/. USDA NASS CDL data is available through https://nassgeodata.gmu.edu/CropScape/. MODIS products are available at https://e4ftl01.cr.usgs.gov/. TROPOMI footprint SIF data is available at ftp://fluo.gps.caltech.edu/data/tropomi/ungridded/. SIF_(OCO2_005) is available at https://cornell.app.box.com/s/cavtg50y80udbdirg022gm5whugmth02. GOME-2 SIF product is available at ftp://fluo.gps.caltech.edu/data/Philipp/GOME-2/. PRISM weather data is available at http://www.prism.oregonstate.edu/.
Funders:
Funding AgencyGrant Number
NASAUNSPECIFIED
NSFUNSPECIFIED
Subject Keywords:Solar-induced Chlorophyll Fluorescence; crop yield; prediction; forecasting; machine learning
Record Number:CaltechAUTHORS:20200422-085520650
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200422-085520650
Official Citation:Bin Peng, Kaiyu Guan, Wang Zhou, Chongya Jiang, Christian Frankenberg, Ying Sun, Liyin He, Philipp Köhler, Assessing the benefit of satellite-based Solar-Induced Chlorophyll Fluorescence in crop yield prediction, International Journal of Applied Earth Observation and Geoinformation, Volume 90, 2020, 102126, ISSN 0303-2434, https://doi.org/10.1016/j.jag.2020.102126. (http://www.sciencedirect.com/science/article/pii/S0303243419313029)
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102713
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:22 Apr 2020 16:05
Last Modified:22 Apr 2020 16:05

Repository Staff Only: item control page