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

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.

[1]  Senthold Asseng,et al.  Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches , 2018, Agricultural and Forest Meteorology.

[2]  Graeme L. Hammer,et al.  Spatial and temporal patterns in Australian wheat yield and their relationship with ENSO , 2002 .

[3]  Gregory Duveiller,et al.  Spatially downscaling sun-induced chlorophyll fluorescence leads to an improved temporal correlation with gross primary productivity , 2016 .

[4]  D. Lobell,et al.  Improving the monitoring of crop productivity using spaceborne solar‐induced fluorescence , 2016, Global change biology.

[5]  Nathaniel K. Newlands,et al.  An integrated, probabilistic model for improved seasonal forecasting of agricultural crop yield under environmental uncertainty , 2014, Front. Environ. Sci..

[6]  Anatoly A. Gitelson,et al.  Relationship between fraction of radiation absorbed by photosynthesizing maize and soybean canopies and NDVI from remotely sensed data taken at close range and from MODIS 250 m resolution data , 2014 .

[7]  Stefano Ermon,et al.  Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data , 2017, AAAI.

[8]  Feng Gao,et al.  The Evaporative Stress Index as an indicator of agricultural drought in Brazil: An assessment based on crop yield impacts , 2016 .

[9]  Dong Jiang,et al.  An artificial neural network model for estimating crop yields using remotely sensed information , 2004 .

[10]  Jian Peng,et al.  Toward building a transparent statistical model for improving crop yield prediction: Modeling rainfed corn in the U.S , 2019, Field Crops Research.

[11]  Wenjiang J. Fu.  Penalized Regressions: The Bridge versus the Lasso , 1998 .

[12]  Ying Sun,et al.  High‐Resolution Global Contiguous SIF of OCO‐2 , 2019, Geophysical Research Letters.

[13]  Jingfeng Xiao,et al.  A Global, 0.05-Degree Product of Solar-Induced Chlorophyll Fluorescence Derived from OCO-2, MODIS, and Reanalysis Data , 2019, Remote. Sens..

[14]  Zhengwei Yang,et al.  Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program , 2011 .

[15]  C. Frankenberg,et al.  Prospects for Chlorophyll Fluorescence Remote Sensing from the Orbiting Carbon Observatory-2 , 2014 .

[16]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[17]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[18]  Balaji Rajagopalan,et al.  The role of ENSO in determining climate and maize yield variability in the U.S. cornbelt , 1999 .

[19]  C. Field,et al.  Canopy near-infrared reflectance and terrestrial photosynthesis , 2017, Science Advances.

[20]  C. Tol,et al.  Linking canopy scattering of far-red sun-induced chlorophyll fluorescence with reflectance. , 2018 .

[21]  C. Frankenberg,et al.  Overview of Solar-Induced chlorophyll Fluorescence (SIF) from the Orbiting Carbon Observatory-2: Retrieval, cross-mission comparison, and global monitoring for GPP , 2018 .

[22]  James W. Jones,et al.  The Agricultural Model Intercomparison and Improvement Project (AgMIP): Protocols and Pilot Studies , 2013 .

[23]  David M. Johnson.  An assessment of pre- and within-season remotely sensed variables for forecasting corn and soybean yields in the United States , 2014 .

[24]  Nicholas C. Parazoo,et al.  Interpreting seasonal changes in the carbon balance of southern Amazonia using measurements of XCO2 and chlorophyll fluorescence from GOSAT , 2013 .

[25]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[26]  Douglas K. Bolton,et al.  Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics , 2013 .

[27]  Aston Chipanshi,et al.  Statistical spring wheat yield forecasting for the Canadian prairie provinces. , 2009 .

[28]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[29]  James Hansen,et al.  Linking dynamic seasonal climate forecasts with crop simulation for maize yield prediction in semi-arid Kenya , 2004 .

[30]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[31]  C. Frankenberg,et al.  A spatially downscaled sun-induced fluorescence global product for enhanced monitoring of vegetation productivity , 2019 .

[32]  C. Frankenberg,et al.  New global observations of the terrestrial carbon cycle from GOSAT: Patterns of plant fluorescence with gross primary productivity , 2011, Geophysical Research Letters.

[33]  John M. Antle,et al.  Toward a new generation of agricultural system data, models, and knowledge products: State of agricultural systems science , 2017, Agricultural systems.

[34]  Jaclyn N. Brown,et al.  Seasonal climate forecasts provide more definitive and accurate crop yield predictions , 2018, Agricultural and Forest Meteorology.

[35]  Vineet Yadav,et al.  Atmospheric CO2 Observations Reveal Strong Correlation Between Regional Net Biospheric Carbon Uptake and Solar‐Induced Chlorophyll Fluorescence , 2017 .

[36]  C. Daly,et al.  Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States , 2008 .

[37]  David M. Legler,et al.  Impact of ENSO-Related Climate Anomalies on Crop Yields in the U.S. , 1999 .

[38]  Louis Kouadio,et al.  Evaluation of the integrated Canadian crop yield forecaster (ICCYF) model for in-season prediction of crop yield across the Canadian agricultural landscape , 2015 .

[39]  P. Gentine,et al.  A global spatially contiguous solar-induced fluorescence (CSIF) dataset using neural networks , 2018, Biogeosciences.

[40]  Scott H. Irwin,et al.  The Impact of Situation and Outlook Information in Corn and Soybean Futures Markets: Evidence from WASDE Reports , 2008, Journal of Agricultural and Applied Economics.

[41]  James W. Jones,et al.  Towards a multiscale crop modelling framework for climate change adaptation assessment , 2020, Nature Plants.

[42]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[43]  W. Bastiaanssen,et al.  A new crop yield forecasting model based on satellite measurements applied across the Indus Basin, Pakistan , 2003 .

[44]  Marco A. S. Netto,et al.  A Scalable Machine Learning System for Pre-Season Agriculture Yield Forecast , 2018, 2018 IEEE 14th International Conference on e-Science (e-Science).

[45]  M. S. Moran,et al.  Global and time-resolved monitoring of crop photosynthesis with chlorophyll fluorescence , 2014, Proceedings of the National Academy of Sciences.

[46]  D. Lobell,et al.  Greater Sensitivity to Drought Accompanies Maize Yield Increase in the U.S. Midwest , 2014, Science.

[47]  Cheryl H. Porter,et al.  A multi-scale and multi-model gridded framework for forecasting crop production, risk analysis, and climate change impact studies , 2019, Environ. Model. Softw..

[48]  Ming Pan,et al.  Benefits of Seasonal Climate Prediction and Satellite Data for Forecasting U.S. Maize Yield , 2018, Geophysical Research Letters.

[49]  James W. Jones,et al.  The DSSAT cropping system model , 2003 .

[50]  Y. Ryu,et al.  A practical approach for estimating the escape ratio of near-infrared solar-induced chlorophyll fluorescence , 2019, Remote Sensing of Environment.

[51]  Xiaocui Wu,et al.  Numerical Terradynamic Simulation Group 2-2018 Regional Crop Gross Primary Productivity and Yield Estimation Using Fused Landsat-MODIS Data , 2018 .

[52]  Christopher B. Field,et al.  Terrestrial gross primary production: Using NIRV to scale from site to globe , 2019, Global change biology.

[53]  J. Landgraf,et al.  Global Retrievals of Solar‐Induced Chlorophyll Fluorescence With TROPOMI: First Results and Intersensor Comparison to OCO‐2 , 2018, Geophysical research letters.

[54]  Y. Cai,et al.  Crop Yield Predictions - High Resolution Statistical Model for Intra-season Forecasts Applied to Corn in the US , 2017 .

[55]  C. Frankenberg,et al.  Towards a Harmonized Long‐Term Spaceborne Record of Far‐Red Solar‐Induced Fluorescence , 2019, Journal of Geophysical Research: Biogeosciences.

[56]  L. Guanter,et al.  Downscaling of solar-induced chlorophyll fluorescence from canopy level to photosystem level using a random forest model , 2019, Remote Sensing of Environment.

[57]  Ying Sun,et al.  A framework for harmonizing multiple satellite instruments to generate a long-term global high spatial-resolution solar-induced chlorophyll fluorescence (SIF) , 2020 .

[58]  Adriano Camps,et al.  L-band vegetation optical depth seasonal metrics for crop yield assessment , 2018, Remote Sensing of Environment.

[59]  Andrew E. Suyker,et al.  Improving maize growth processes in the community land model: Implementation and evaluation , 2018 .

[60]  Roger Stone,et al.  Enhanced risk management and decision-making capability across the sugarcane industry value chain based on seasonal climate forecasts , 2002 .

[61]  Martha C. Anderson,et al.  The shared and unique values of optical, fluorescence, thermal and microwave satellite data for estimating large-scale crop yields. , 2016 .

[62]  Jonathan P. Resop,et al.  Random Forests for Global and Regional Crop Yield Predictions , 2016, PloS one.

[63]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[64]  Wout Verhoef,et al.  The FLuorescence EXplorer Mission Concept—ESA’s Earth Explorer 8 , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[65]  Martha C. Anderson,et al.  Field-scale mapping of evaporative stress indicators of crop yield: An application over Mead, NE, USA , 2018, Remote Sensing of Environment.

[66]  D. Lobell,et al.  A scalable satellite-based crop yield mapper , 2015 .

[67]  C. Frankenberg,et al.  Global monitoring of terrestrial chlorophyll fluorescence from moderate-spectral-resolution near-infrared satellite measurements: methodology, simulations, and application to GOME-2 , 2013 .

[68]  C. Frankenberg,et al.  Connecting active to passive fluorescence with photosynthesis: a method for evaluating remote sensing measurements of Chl fluorescence. , 2017, The New phytologist.

[69]  D. Lobell,et al.  On the use of statistical models to predict crop yield responses to climate change , 2010 .