Two Shifts for Crop Mapping: Leveraging Aggregate Crop Statistics to Improve Satellite-based Maps in New Regions

Abstract Crop type mapping at the field level is critical for a variety of applications in agricultural monitoring, and satellite imagery is becoming an increasingly abundant and useful raw input from which to create crop type maps. Still, in many regions crop type mapping with satellite data remains constrained by a scarcity of field-level crop labels for training supervised classification models. When training data is not available in one region, classifiers trained in similar regions can be transferred, but shifts in the distribution of crop types as well as transformations of the features between regions lead to reduced classification accuracy. We present a methodology that uses aggregate-level crop statistics to correct the classifier by accounting for these two types of shifts. To adjust for shifts in the crop type composition we present a scheme for properly reweighting the posterior probabilities of each class that are output by the classifier. To adjust for shifts in features we propose a method to estimate and remove linear shifts in the mean feature vector. We demonstrate that this methodology leads to substantial improvements in overall classification accuracy when using Linear Discriminant Analysis (LDA) to map crop types in Occitanie, France and in Western Province, Kenya. When using LDA as our base classifier, we found that in France our methodology led to percent reductions in misclassifications ranging from 2.8% to 42.2% (mean = 21.9%) over eleven different training departments, and in Kenya the percent reductions in misclassification were 6.6%, 28.4%, and 42.7% for three training regions. While our methodology was statistically motivated by the LDA classifier, it can be applied to any type of classifier. As an example, we demonstrate its successful application to improve a Random Forest classifier.

[1]  Gérard Dedieu,et al.  Near real-time agriculture monitoring at national scale at parcel resolution: Performance assessment of the Sen2-Agri automated system in various cropping systems around the world , 2019, Remote Sensing of Environment.

[2]  Ryosuke Shibasaki,et al.  A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation , 2020, Remote. Sens..

[3]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[4]  Luis Guanter,et al.  Ready-to-Use Methods for the Detection of Clouds, Cirrus, Snow, Shadow, Water and Clear Sky Pixels in Sentinel-2 MSI Images , 2016, Remote. Sens..

[5]  A. Viña,et al.  Remote estimation of canopy chlorophyll content in crops , 2005 .

[6]  David B. Lobell,et al.  Smallholder maize area and yield mapping at national scales with Google Earth Engine , 2019, Remote Sensing of Environment.

[7]  Shawki Areibi,et al.  Domain Adaptation Using Representation Learning for the Classification of Remote Sensing Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  David B. Lobell,et al.  Crop type mapping without field-level labels: Random forest transfer and unsupervised clustering techniques , 2019, Remote Sensing of Environment.

[9]  Steffen Fritz,et al.  Mapping Priorities to Focus Cropland Mapping Activities: Fitness Assessment of Existing Global, Regional and National Cropland Maps , 2015, Remote. Sens..

[10]  Gang Fu,et al.  Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network , 2017, Remote. Sens..

[11]  D. Medak,et al.  Contemporary comparative assessment of atmospheric correction influence on radiometric indices between Sentinel-2A and Landsat 8 imagery , 2019, Geocarto International.

[12]  Stefano Ermon,et al.  Deep Transfer Learning for Crop Yield Prediction with Remote Sensing Data , 2018, COMPASS.

[13]  Tiziana Simoniello,et al.  A first assessment of the Sentinel-2 Level 1-C cloud mask product to support informed surface analyses , 2018, Remote Sensing of Environment.

[14]  Li Pan,et al.  Category-Sensitive Domain Adaptation for Land Cover Mapping in Aerial Scenes , 2019, Remote. Sens..

[15]  Luís Torgo,et al.  UBL: an R package for Utility-based Learning , 2016, ArXiv.

[16]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[17]  Liangzhi You,et al.  Generating Global Crop Distribution Maps: From Census to Grid , 2014 .

[18]  Rafael Pires de Lima,et al.  Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis , 2019, Remote. Sens..

[19]  Shaowen Wang,et al.  A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach , 2018, Remote Sensing of Environment.

[20]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

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

[22]  Philipp Berens,et al.  The art of using t-SNE for single-cell transcriptomics , 2018, Nature Communications.

[23]  Fabian Löw,et al.  The impact of training class proportions on binary cropland classification , 2017 .

[24]  D. Legates,et al.  Crop identification using harmonic analysis of time-series AVHRR NDVI data , 2002 .

[25]  Marco Saerens,et al.  Adjusting the Outputs of a Classifier to New a Priori Probabilities: A Simple Procedure , 2002, Neural Computation.

[26]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[27]  Amos Storkey,et al.  When Training and Test Sets are Different: Characterising Learning Transfer , 2013 .

[28]  Yang Chen,et al.  Needle in a haystack: Mapping rare and infrequent crops using satellite imagery and data balancing methods , 2019, Remote Sensing of Environment.

[29]  Damir Medak,et al.  Impact of Various Atmospheric Corrections on Sentinel-2 Land Cover Classification Accuracy Using Machine Learning Classifiers , 2020, ISPRS Int. J. Geo Inf..