Cropland parcels are the basic unit for agricultural production, and their size and shape may change due to human activities, e.g., land consolidation. Remote sensing has been increasingly used for mapping cropland parcel, yet detecting changes in cropland parcels by wall-to-wall mapping is time-consuming. This paper proposes a new algorithm to identify whether and where cropland parcel changes have been undertaken without generating complete parcel maps. We use the number of edge pixels derived from remote sensing imagery as a proxy indicator for cropland parcel changes. First, we apply a Sobel operator to delineate the total edge pixels of parcels from dual-time images. Second, we apply the connected-components labeling to remove pseudo-edges arising from non-cropland built structures and transmission towers. We then perform topological optimization, including morphological dilation and skeleton extraction, to eliminate redundant edge pixels for parcel structure. Finally, we detect whether parcel changes have been undertaken by counting and comparing the number of edge pixels derived from dual-time images. We applied this innovative framework in five regions in East Asia where land consolidation has significantly changed cropland parcels. Our method demonstrated robust detection results, with stable accuracy, precision, recall, and F1-score, all exceeding 0.85. Screening redundant edge pixels reduced noise and permitted efficient detection of changes in cropland parcels. Our method extends the traditional detection of semantic change to structural change and can quickly detect cropland parcel changes with high accuracy. This capability offers the potential to identify hotspot areas of cropland changes on a larger scale without the need to produce full cropland maps, which is particularly useful for monitoring land consolidation programs.
- Article type
- Year
- Co-author
Open Access
Research Article
Issue
Cropping systems of cropland are the concrete embodiment of the mode of agricultural production, which reflect the coupled human-environment interactions. The formation is affected by natural resource elements and human land use behavior. This study aims to scientifically understand the spatial-temporal pattern of cropping systems, which helps to optimize agricultural distribution, improve agricultural production capacity, and realize the sustainable agriculture.
This study combined remote sensing monitoring with spatial decision tree models and other means to construct an inter-annual detection method system for cropping systems, which is designed for Chinese agricultural conditions, and then spatial pattern of cropping systems was analyzed. Firstly, the connotation of cropping systems was defined by identifying concepts such as cropping intensity, multiple cropping index, and considering of characteristics of “long-lasting” “periodicity” “stability”. Secondly, the indicators (i.e. continuity and frequency) were constructed, and were calculated at the pixel scale by the moving time window. Finally, the significance of the cropping intensity and characteristics of cropping system was evaluated. The decision tree method was also applied to determine the type of cropping systems, and the spatial-temporal heterogeneity of cropping systems in different regions was analyzed from the aspects of regional differences and dynamic laws.
(1) Quantitatively, the largest area, 53.52%, is occupied by the single-cropping system, followed by the double-cropping system at 23.28%, the seasonal fallow system (i.e. 3 crops in 2 years) and the annual fallow system at 12.80% and 6.94%, respectively. (2) Spatially, the single-cropping system, double-cropping system, seasonal fallow system and annual fallow system are concentrated in Northeast China, North China, South of Yangtze River and “Sickle Bend” areas, respectively. (3) Temporally, it revealed the heterogeneity of cropping system and static multiple cropping index in the time dimension. For example, the regions with multiple cropping index of 1 in 2018 consist of 75.18% single-cropping system, 6.60% double-cropping system, 8.92% seasonal fallow system and 8.02% annual fallow system.
This study proposed a method for mapping inter-annual cropping systems, combining remote sensing temporal monitoring and spatial decision tree models. It revealed the spatial pattern of cropping systems which is gathered by zone and cropping intensity is higher in the south and lower in the north. The Songnen Plain, “Sickle Bend” and other spatial gathering areas were intuitively displayed. Also, the differences between multi-cropping and cropping system were compared, which were mainly manifested in the spatial inconsistency between the cropping system and the annual multiple cropping index, as well as the periodicity of the cropping system. The results will provide case support for rationally increasing the cropland multi-cropping intensity and promoting the implementation of the “grain storage in the ground” strategy.
京公网安备11010802044758号