Monitoring Within-Field Variability of Corn Yield using Sentinel-2 and Machine Learning Techniques

Monitoring and prediction of within-field crop variability can support farmers to make the right decisions in different situations. The current advances in remote sensing and the availability of high resolution, high frequency, and free Sentinel-2 images improve the implementation of Precision Agriculture (PA) for a wider range of farmers. This study investigated the possibility of using vegetation indices (VIs) derived from Sentinel-2 images and machine learning techniques to assess corn (Zea mays) grain yield spatial variability within the field scale. A 22-ha study field in North Italy was monitored between 2016 and 2018; corn yield was measured and recorded by a grain yield monitor mounted on the harvester machine recording more than 20,000 georeferenced yield observation points from the study field for each season. VIs from a total of 34 Sentinel-2 images at different crop ages were analyzed for correlation with the measured yield observations. Multiple regression and two different machine learning approaches were also tested to model corn grain yield. The three main results were the following: (i) the Green Normalized Difference Vegetation Index (GNDVI) provided the highest R2 value of 0.48 for monitoring within-field variability of corn grain yield; (ii) the most suitable period for corn yield monitoring was a crop age between 105 and 135 days from the planting date (R4–R6); (iii) Random Forests was the most accurate machine learning approach for predicting within-field variability of corn yield, with an R2 value of almost 0.6 over an independent validation set of half of the total observations. Based on the results, within-field variability of corn yield for previous seasons could be investigated from archived Sentinel-2 data with GNDVI at crop stage (R4–R6).

[1]  D. Mulla.  Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps , 2013 .

[2]  Gary E. Varvel,et al.  Use of Remote-Sensing Imagery to Estimate Corn Grain Yield , 2001 .

[3]  Francesco Pirotti,et al.  BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE , 2016 .

[4]  A. Gitelson,et al.  Use of a green channel in remote sensing of global vegetation from EOS- MODIS , 1996 .

[5]  Sebastian Varela,et al.  Forecasting maize yield at field scale based on high-resolution satellite imagery , 2018, Biosystems Engineering.

[6]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[7]  Ranga B. Myneni,et al.  Using hyperspectral vegetation indices to estimate the fraction of photosynthetically active radiation absorbed by corn canopies , 2013 .

[8]  Julien Morel,et al.  Toward a Satellite-Based System of Sugarcane Yield Estimation and Forecasting in Smallholder Farming Conditions: A Case Study on Reunion Island , 2014, Remote. Sens..

[9]  A. Kayad,et al.  Assessing the Spatial Variability of Alfalfa Yield Using Satellite Imagery and Ground-Based Data , 2016, PloS one.

[10]  Juan J. Flores,et al.  The application of artificial neural networks to the analysis of remotely sensed data , 2008 .

[11]  Heather McNairn,et al.  International Journal of Applied Earth Observation and Geoinformation , 2014 .

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

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

[14]  David W. Franzen,et al.  Comparison of Satellite Imagery and Ground-Based Active Optical Sensors as Yield Predictors in Sugar Beet, Spring Wheat, Corn, and Sunflower , 2017 .

[15]  Andrew E. Suyker,et al.  Estimating daily gross primary production of maize based only on MODIS WDRVI and shortwave radiation data , 2011 .

[16]  Nari Kim,et al.  Machine Learning Approaches to Corn Yield Estimation Using Satellite Images and Climate Data :A Case of Iowa State , 2016 .

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

[18]  J. I. Ortiz-Monasterio,et al.  Combining Field Surveys, Remote Sensing, and Regression Trees to Understand Yield Variations in an Irrigated Wheat Landscape , 2005, Agronomy Journal.

[19]  Anatoly A. Gitelson,et al.  MODIS-based corn grain yield estimation model incorporating crop phenology information , 2013 .

[20]  Weixing Cao,et al.  Assimilating Remotely Sensed Information with the WheatGrow Model Based on the Ensemble Square Root Filter forImproving Regional Wheat Yield Forecasts , 2013 .

[21]  Bruno Basso,et al.  Predicting spatial patterns of within-field crop yield variability , 2018 .

[22]  Claudia Notarnicola,et al.  Review of Machine Learning Approaches for Biomass and Soil Moisture Retrievals from Remote Sensing Data , 2015, Remote. Sens..

[23]  Guijun Yang,et al.  A Comparison of Regression Techniques for Estimation of Above-Ground Winter Wheat Biomass Using Near-Surface Spectroscopy , 2018, Remote. Sens..

[24]  Baofeng Su,et al.  Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications , 2017, J. Sensors.

[25]  K. Al-Gaadi,et al.  Characterization of the spatial variability of surface topography and moisture content and its influence on potato crop yield , 2018, International Journal of Remote Sensing.

[26]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[27]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[28]  Raghavan Srinivasan,et al.  Using Satellite and Field Data with Crop Growth Modeling to Monitor and Estimate Corn Yield in Mexico , 2002 .

[29]  Sudhanshu Sekhar Panda,et al.  Application of Vegetation Indices for Agricultural Crop Yield Prediction Using Neural Network Techniques , 2010, Remote. Sens..

[30]  G. Timár,et al.  Yield forecasting for wheat and corn in Hungary by satellite remote sensing , 2011 .

[31]  Andrew Robson,et al.  Exploring the Potential of High Resolution WorldView-3 Imagery for Estimating Yield of Mango , 2018, Remote. Sens..

[32]  George Alan Blackburn,et al.  High resolution wheat yield mapping using Sentinel-2 , 2019, Remote Sensing of Environment.

[33]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[34]  C. Tucker,et al.  Remote Sensing of Total Dry-Matter Accumulation in Winter Wheat , 1981 .

[35]  Shusen Wang,et al.  Crop yield forecasting on the Canadian Prairies using MODIS NDVI data , 2011 .

[36]  G. Timár,et al.  Crop yield estimation by satellite remote sensing , 2004 .

[37]  F. Marinello,et al.  Using SALUS Model for Medium and Long Term Simulations of Energy Efficiency in Different Tillage Systems , 2014 .

[38]  Xiaodong Yang,et al.  Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data , 2019, Plant Methods.

[39]  Craig S. T. Daughtry,et al.  Assessing the Variability of Corn and Soybean Yields in Central Iowa Using High Spatiotemporal Resolution Multi-Satellite Imagery , 2018, Remote. Sens..

[40]  D. Lobell,et al.  Satellite-based assessment of yield variation and its determinants in smallholder African systems , 2017, Proceedings of the National Academy of Sciences.

[41]  Juan Du,et al.  Mid-Season High-Resolution Satellite Imagery for Forecasting Site-Specific Corn Yield , 2016, Remote. Sens..

[42]  David B. Lobell,et al.  Testing Remote Sensing Approaches for Assessing Yield Variability among Maize Fields , 2014 .

[43]  Huanhuan Yuan,et al.  Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models , 2017, Remote. Sens..

[44]  Kenton W. Ross,et al.  Review of Intra-Field Yield Estimation from Yield Monitor Data , 2008 .

[45]  B. Bouman,et al.  Crop modelling and remote sensing for yield prediction , 1995 .

[46]  Claire Marais-Sicre,et al.  Estimation of corn yield using multi-temporal optical and radar satellite data and artificial neural networks , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[47]  O. Rojas.  Operational maize yield model development and validation based on remote sensing and agro‐meteorological data in Kenya , 2007 .

[48]  Francesco Marinello,et al.  Last generation instrument for agriculture multispectral data collection , 2017 .

[49]  S. Prasher,et al.  Application of support vector machine technology for weed and nitrogen stress detection in corn , 2006 .

[50]  Ghassem R. Asrar,et al.  Estimates of leaf area index from spectral reflectance of wheat under different cultural practices and solar angle , 1985 .

[51]  A. F. Colaço,et al.  Do crop sensors promote improved nitrogen management in grain crops , 2018 .

[52]  Jiali Shang,et al.  Using spatio-temporal fusion of Landsat-8 and MODIS data to derive phenology, biomass and yield estimates for corn and soybean. , 2019, The Science of the total environment.

[53]  A. Kayad,et al.  Prediction of Potato Crop Yield Using Precision Agriculture Techniques , 2016, PloS one.

[54]  A. Gitelson.  Wide Dynamic Range Vegetation Index for remote quantification of biophysical characteristics of vegetation. , 2004, Journal of plant physiology.

[55]  Andrea Masiero,et al.  Open source R for applying machine learning to RPAS remote sensing images , 2017, Open Geospatial Data, Software and Standards.

[56]  David B. Lobell,et al.  The use of satellite data for crop yield gap analysis , 2013 .

[57]  Jiahua Zhang,et al.  Estimation of maize yield by using a process-based model and remote sensing data in the Northeast China Plain , 2015 .

[58]  Mark Trotter,et al.  Objective biomass assessment using an active plant sensor (Crop Circle™) - preliminary experiences on a variety of agricultural landscapes , 2008 .

[59]  S. Dutta,et al.  Study of crop growth parameters using Airborne Imaging Spectrometer data , 2001 .

[60]  Sujit Kumar Bala,et al.  Correlation between potato yield and MODIS‐derived vegetation indices , 2009 .