In-Season Major Crop-Type Identification for US Cropland from Landsat Images Using Crop-Rotation Pattern and Progressive Data Classification

Md Shahinoor Rahman,Chen Zhang,Hossain Mohiuddin,Liping Di,Eugene Yu

doi:10.3390/agriculture9010017

Md Shahinoor Rahman, Chen Zhang + Show 3 more

Open Access

https://doi.org/10.3390/agriculture9010017

Copy DOI

Journal: Agriculture	Publication Date: Jan 9, 2019
Citations: 21	License type: CC BY 4.0

Affiliation: George Mason University, University of Iowa

Abstract

Crop type information at the field level is vital for many types of research and applications. The United States Department of Agriculture (USDA) provides information on crop types for US cropland as a Cropland Data Layer (CDL). However, CDL is only available at the end of the year after the crop growing season. Therefore, CDL is unable to support in-season research and decision-making regarding crop loss estimation, yield estimation, and grain pricing. The USDA mostly relies on field survey and farmers’ reports for the ground truth to train image classification models, which is one of the major reasons for the delayed release of CDL. This research aims to use trusted pixels as ground truth to train classification models. Trusted pixels are pixels which follow a specific crop rotation pattern. These trusted pixels are used to train image classification models for the classification of in-season Landsat images to identify major crop types. Six different classification algorithms are investigated and tested to select the best algorithm for this study. The Random Forest algorithm stands out among selected algorithms. This study classified Landsat scenes between May and mid-August for Iowa. The overall agreements of classification results with CDL in 2017 are 84%, 94%, and 96% for May, June, and July, respectively. The classification accuracies have been assessed through 683 ground truth data points collected from the fields. The overall accuracies of single date multi-band image classification are 84%, 89% and 92% for May, June, and July, respectively. The result also shows higher accuracy (94–95%) can be achieved through multi-date image classification compared to single date image classification.

Highlights

Crop-specific acreage information, such as crop types with their location, is useful for crop statistics, yield estimation, change in cropland use, cropland environmental dynamics, crop loss assessment, crop pricing, decision support, and policy formulation [1]
In-season crop type identification is crucial for research and decision-making processes
Crop-specific information is only available at the end of the year, many months after the crop growing season

Summary

Introduction

Crop-specific acreage information, such as crop types with their location, is useful for crop statistics, yield estimation, change in cropland use, cropland environmental dynamics, crop loss assessment, crop pricing, decision support, and policy formulation [1]. Generating yearly or seasonal information for each crop field at the regional scale is not a trivial task in any part of the world. Field survey-based information collection has been replaced using satellite images. Information can be extracted from satellite images multiple times within or outside of the growing season. Satellite images are useful for crop condition monitoring, growth stage monitoring, and loss assessment. The use of satellite images in crop type identification is time and cost effective over vast areas. The National Agricultural Statistics Service (NASS) of the US Department of Agriculture (USDA) probably

Objectives

Methods

Results

Conclusion