Chapter 17
Remote Sensing–Based Mapping
of Plastic-Mulched Land Cover
Lizhen Lu
Abstract Plastic-mulched land cover (PML) has been expanding rapidly worldwide
and formed a significant agriculture landscape in recent two decades; therefore,
mapping PML from remote sensing images is an important agricultural monitoring
task. This chapter introduces three effective PML mapping methods from remotely
sensed data: a decision-tree classifier for extracting the transparent PML information
from Landsat-5 TM images, a threshold model (TM) for PML detection and
mapping with moderate-resolution imaging spectroradiometer (MODIS) time series
data, and an improved spatial attraction model (ISAM) for PML subpixel mapping
using the soft classification results from MODIS bands 1–2 and sharpened bands
3–7 data.
Keywords Plastic-mulched land cover · Decision-tree classifier · Threshold model ·
Subpixel mapping · Improved spatial attraction model · Remote sensing time series
data
17.1 Introduction
Plastic-covered farmland, or plasticulture, in the broad sense, is defined as the use of
plastic films in agriculture (Dubois 1978; Orzolek 1999; Takakura and Fang 2002).
The purposes of using plastic cover in agriculture are to mitigate the threats of
insects, crop diseases, coldness, heat, drought, and strong rainfall and wind and to
improve productivity (Takakura and Fang 2002; Lu et al. 2014). Plastic-mulched
land cover (PML), greenhouse or walk-in tunnels, and small tunnels are three main
types of plasticulture (see Fig. 17.1).
The area of plasticulture has been expanding rapidly worldwide over the last two
decades and now represents an important agricultural landscape (Espí et al. 2006; Lu
L. Lu (*)
Zhejiang University, Hangzhou, China
e-mail: llz_gis@zju.edu.cn
© Springer Nature Switzerland AG 2021
L. Di, B. Üstündağ (eds.), Agro-geoinformatics, Springer Remote Sensing/
Photogrammetry, https://doi.org/10.1007/978-3-030-66387-2_17
351
Remote Sensing–Based Mapping
of Plastic-Mulched Land Cover
Lizhen Lu
Abstract Plastic-mulched land cover (PML) has been expanding rapidly worldwide
and formed a significant agriculture landscape in recent two decades; therefore,
mapping PML from remote sensing images is an important agricultural monitoring
task. This chapter introduces three effective PML mapping methods from remotely
sensed data: a decision-tree classifier for extracting the transparent PML information
from Landsat-5 TM images, a threshold model (TM) for PML detection and
mapping with moderate-resolution imaging spectroradiometer (MODIS) time series
data, and an improved spatial attraction model (ISAM) for PML subpixel mapping
using the soft classification results from MODIS bands 1–2 and sharpened bands
3–7 data.
Keywords Plastic-mulched land cover · Decision-tree classifier · Threshold model ·
Subpixel mapping · Improved spatial attraction model · Remote sensing time series
data
17.1 Introduction
Plastic-covered farmland, or plasticulture, in the broad sense, is defined as the use of
plastic films in agriculture (Dubois 1978; Orzolek 1999; Takakura and Fang 2002).
The purposes of using plastic cover in agriculture are to mitigate the threats of
insects, crop diseases, coldness, heat, drought, and strong rainfall and wind and to
improve productivity (Takakura and Fang 2002; Lu et al. 2014). Plastic-mulched
land cover (PML), greenhouse or walk-in tunnels, and small tunnels are three main
types of plasticulture (see Fig. 17.1).
The area of plasticulture has been expanding rapidly worldwide over the last two
decades and now represents an important agricultural landscape (Espí et al. 2006; Lu
L. Lu (*)
Zhejiang University, Hangzhou, China
e-mail: llz_gis@zju.edu.cn
© Springer Nature Switzerland AG 2021
L. Di, B. Üstündağ (eds.), Agro-geoinformatics, Springer Remote Sensing/
Photogrammetry, https://doi.org/10.1007/978-3-030-66387-2_17
351