Identification of Seed Maize Fields With High Spatial Resolution and Multiple Spectral Remote Sensing Using Random Forest Classifier

Lin Zhang; Zhe Liu; Tianwei Ren; Diyou Liu; Zhe Ma; Liang Tong; Chao Zhang; Tianying Zhou; Xiaodong Zhang; Shaoming Li

doi:10.3390/rs12030362

Remote Sensing (Jan 2020)

Identification of Seed Maize Fields With High Spatial Resolution and Multiple Spectral Remote Sensing Using Random Forest Classifier

Lin Zhang,
Zhe Liu,
Tianwei Ren,
Diyou Liu,
Zhe Ma,
Liang Tong,
Chao Zhang,
Tianying Zhou,
Xiaodong Zhang,
Shaoming Li

Affiliations

Lin Zhang: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Zhe Liu: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Tianwei Ren: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Diyou Liu: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Zhe Ma: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Liang Tong: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Chao Zhang: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Tianying Zhou: GIS Research Center, Feng Chia University, Taichung City 407, Taiwan
Xiaodong Zhang: College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Shaoming Li: College of Land Science and Technology, China Agricultural University, Beijing 100083, China

DOI: https://doi.org/10.3390/rs12030362
Journal volume & issue: Vol. 12, no. 3
p. 362

Abstract

Read online

Seed maize and common maize plots have different planting patterns and variety types. Identification of seed maize is the basis for seed maize growth monitoring, seed quality and common maize seed supply. In this paper, a random forest (RF) classifier is used to develop an approach for seed maize fields’ identification, using the time series vegetation indexes (VIs) calculated from multispectral data acquired from Landsat 8 and Gaofen 1 satellite (GF-1), field sample data, and texture features of Gaofen 2 satellite (GF-2) panchromatic data. Huocheng and Hutubi County in the Xinjiang Uygur Autonomous Region of China were chosen as study area. The results show that RF performs well with the combination of six VIs (normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), triangle vegetation index (TVI), ratio vegetation index (RVI), normalized difference water index (NDWI) and difference vegetation index (DVI)) and texture features based on a grey-level co-occurrence matrix. The classification based on “spectrum + texture” information has higher overall, user and producer accuracies than that of spectral information alone. Using the “spectrum + texture” method, the overall accuracy of classification in Huocheng County is 95.90%, the Kappa coefficient is 0.92, and the producer accuracy for seed maize fields is 93.91%. The overall accuracy of the classification in Hutubi County is 97.79%, the Kappa coefficient is 0.95, and the producer accuracy for seed maize fields is 97.65%. Therefore, RF classifier inputted with high-resolution remote-sensing image features can distinguish two kinds of planting patterns (seed and common) and varieties types (inbred and hybrid) of maize and can be used to identify and map a wide range of seed maize fields. However, this method requires a large amount of sample data, so how to effectively use and improve it in areas lacking samples needs further research.

Published in Remote Sensing

ISSN: 2072-4292 (Online)
Publisher: MDPI AG
Country of publisher: Switzerland
LCC subjects: Science
Website: http://www.mdpi.com/journal/remotesensing/

About the journal

Abstract

Keywords