通过协同方法识别和量化全球耕地面积比较中的地方不确定性和差异

 耕地制图
 协同图
 数据融合
SOSA
 空间一致性

of cropland changes. The CLCD datasets have been rigorously compared to state-of-the-art $30-\mathrm{m}$$30-\mathrm{m}$30-m30-\mathrm{m} resolution thematic products including forest, surface water, and impervious surface area (ISA) to comprehensively assess its property, but few have been compared to cropland (Zhang et al., 2022). Another noteworthy dataset is the Global Land Cover-FCS30 (GLC_FCS30), a global land cover dynamic monitoring product. It adopts an exemplary classification system derived from surface reflectance (SR) images and local adaptive modeling, integrating the Food and Agriculture Organization of the United Nations (FAO) classification system to categorize land cover into 29 classes (Zhang et al., 2021). Globeland30, the world’s first 30-m resolution global land cover dataset, amalgamates multispectral imagery from the US Landsat and the China Disaster Monitoring Constellation (DMC). It employs the innovative Pixel-Object-Knowledge (POK) hierarchical classification method to classify land cover into 10 categories (Brovelli et al., 2015). GlobalCrop, in contrast, leverages normalized SR data from Landsat Analysis Ready Data (ARD) as input for mapping, generating a probability layer for each pixel via a bagged decision tree ensemble to creat a global cropland map (Potapov et al., 2021). While GlobalCrop is one year apart from the other datasets, careful studies have demonstrated that the land use and land cover changes during this period, on a large scale, are almost negligible when compared to classification error. The European Space Agency (ESA) Climate Change Initiative (CCI) project has contributed a suite of satellite-based products that incorporate medium-resolution imaging spectrometer (MERIS) SR time-series configuration parameters as input to generate land cover maps, enabling lengthy observations and analysis of global land cover dynamics since the 1990s (Zhong et al., 2022). 

A unified classification system is a prerequisite for contrasting data products from various sources (Hua et al., 2018). Opting for a simplified classification helps mitigate uncertainty that can arise from the wide variety of detailed land cover types (Nabil et al., 2020). To achieve this, we reclassified the datasets into cropland and non-cropland while retaining the cropland category’s information. We excluded the effects of other classes and selected the relevant types in each dataset for merging, adhering to the FAO definition of cropland. Thereinto, cropland includes arable lands, which encompass areas under temporary agricultural crops, land used for market and kitchen gardens, temporary meadows for mowing or grazing, and temporarily fallow land. Permanent crops encompass long-term crops that are sown above ground and do not require replanting for many years, flower crops that can grow under trees and shrubs, and nurseries. Additionally, cropland-related classes in each dataset were extracted and assigned percentage weights in compliance with their definitions (i.e. mosaic cropland classes received lower weights, while pure cropland classes were given higher percentage weights). This process generated percentage maps of cropland at a $300-\mathrm{m}$$300-\mathrm{m}$300-m300-\mathrm{m} resolution, all in the same coordinate system, for each satellite-based dataset. 

In Fig. 2, we present the geographical distribution of China’s cropland around 2020, which has been extracted from five existing datasets, along with the training samples obtained from the Second National Land Survey (SNLS) database. SNLS implemented a unified organizational model that combined government coordination, local field surveys, and national quality control. It was established on the foundation of a survey base map that encompassed the entire range of remote sensing images, ensuring consistency between maps, figures, and real-world observations (Zhong et al., 2022). To maintain the accuracy and relevance of geospatial information, the Ministry of Natural Resources has overseen an annual survey of territorial changes and updates to the SNLS results since 2010. These map delineation data were meticulously verified by local experts who relied on both remote sensing images and field surveys (Chen et al., 2023; Liu et al., 2015). The existence of independent operating systems and a substantial financial assistance budget have further bolstered the credibility of accurate, comparable, systematic, 

Additionally, the geographic distribution of cropland is regularly constrained by natural factors, such as topography, which poses certain intractability for remote sensing mapping (Zhang et al., 2022), hence further exploring their consistency in terms of altitude and slope within each landform interval. Of which, altitudes and slopes were calculated according to digital elevation models (DEM) that sprang from the integration of SRTM (Shuttle Radar Topography Mission) processing upgrades, vertical control, void filling, and merging with data unavailable at the time of the original SRTM formation (https://www.earthdata. nasa.gov/). Besides, the cropland statistics were obtained from the China Statistical Yearbook, published by the National Bureau of Statistics (NBS) (http://www.stats.gov.cn/), which counted the cropland acreage in each of provinces, municipalities, and autonomous regions and their proportion in the entire country. The cropland training samples were sourced from the foundational data of the SNLS, which was collected and compiled by the Ministry of Natural Resources of the People’s 

中华民国（前称国土资源部）(https://www.mnr.gov.cn/sj/).

Consistency assessment is a method used to evaluate the reliability of multi-source products in the absence of objective reference criteria. It is typically employed for mutual validation between datasets (Hua et al., 2018). This approach operates under the assumption that the data and methods employed in each land cover dataset are reasonable. Each data product is expected to approximate the true value of land cover to varying degrees. In other words, a significant portion of the data aligns with, or closely represents, the actual situation, while there is also a fraction of misjudged data (Lu et al., 2017). In this approach, each set of products is treated as an expert judgment of the actual status. The agreement level between the judgments of different datasets concerning the land cover type or quantitative characteristics of a given spatial unit or period is used as an indicator to assess the likelihood of the data’s reliability (Chen et al., 2019). The consistency ratio (CR) is defined as follows: 
$C{R}_j=\frac{M_j}{\frac{1}{k}\sum _{j=1}^k{N}_j}\times 100\mathrm{\%}$$C{R}_j=\frac{M_j}{\frac{1}{k}\sum _{j=1}^k N_j}\times 100\mathrm{\%}$CR_(j)=(M_(j))/((1)/(k)sum_(j=1)^(k)N_(j))xx100%C R_{j}=\frac{M_{j}}{\frac{1}{k} \sum_{j=1}^{k} N_{j}} \times 100 \%
where: $M_j$$M_j$M_(j)M_{j} denotes the pixel amount of product $j$$j$jj whose cover type is cropland at the same position; $N_j$$N_j$N_(j)N_{j} denotes the pixel amount of cropland in product $j;k$$j;k$j;kj ; k denotes the number of cropland products. The higher the consistency, the more likely the data product is to be robust (Fritz et al., 2011). 

To evaluate the agreement and discrepancies between the cropland products and the survey data, we computed the Root Mean Square Error (RMSE) for each dataset compared to the official statistics based on cropland proportion. Simultaneously, we conducted a correlation analysis between the datasets and the survey data. The RMSE and correlation coefficient $(R)$$(R)$(R)(R) were calculated as follows (Pérez-Hoyos et al., 2017): 

where: $x_i$$x_i$x_(i)x_{i} and $\overline{x}$$\overline{x}$bar(x)\bar{x} are the area ratio of unit $i$$i$ii and the average area ratio of all units computed in the cropland datasets; $y_i$$y_i$y_(i)y_{i} and $\overline{y}$$\overline{y}$bar(y)\bar{y} are the statistical area ratio of unit $i$$i$ii and the average of the acreage ratio of the statistics, respectively; $n$$n$nn denotes the number of units. The larger the RMSE, the higher the dispersion, while a larger $R$$R$RR refers to a higher goodness of fit (Claverie et al., 2013). 

The confusion matrix, one of the most commonly employed evaluation methods in satellite mapping, serves as a fundamental metric for assessing the accuracy of different products (Brovelli et al., 2015). The evaluation of classification accuracy in China is based on the confusion matrix of five sets of global land cover data and test samples, resulting in the computation of the Kappa coefficient, overall accuracy ( $OA$$OA$OAO A ), omission error, and commission error. 
$OA=\frac{\sum _{i=1}^n{x}_{ii}}{N}$$OA=\frac{\sum _{i=1}^n x_{ii}}{N}$OA=(sum_(i=1)^(n)x_(ii))/(N)O A=\frac{\sum_{i=1}^{n} x_{i i}}{N}
 卡拉 $=\frac{N\sum _{i=1}^n{x}_{ii}-\sum _{i=1}^n{x}_i{x}_j}{N^2-\sum _{i=1}^n{x}_i{x}_j}$$=\frac{N\sum _{i=1}^n x_{ii}-\sum _{i=1}^n x_i{x}_j}{N^2-\sum _{i=1}^n x_i{x}_j}$=(Nsum_(i=1)^(n)x_(ii)-sum_(i=1)^(n)x_(i)x_(j))/(N^(2)-sum_(i=1)^(n)x_(i)x_(j))=\frac{N \sum_{i=1}^{n} x_{i i}-\sum_{i=1}^{n} x_{i} x_{j}}{N^{2}-\sum_{i=1}^{n} x_{i} x_{j}}
where: $N$$N$NN denotes the total of participating samples; $n$$n$nn is the confusion matrix dimension; $x_{ii}$$x_{ii}$x_(ii)x_{i i} is the number of samples in the diagonal; $x_j$$x_j$x_(j)x_{j} and $x_i$$x_i$x_(i)x_{i} denote the total of samples in column $j$$j$jj and row $i$$i$ii. 

The protocol level plays a critical role in the integration of various remote sensing maps to develop an enriched dataset (See et al., 2015). Initially, subnational statistics were employed to assess accuracy and establish weights for the input cropland maps. It’s worth noting that the quality of the input products being evaluated can significantly impact the confidence of the synergy. Subsequently, agreement ranking scores were determined based on this accuracy and protocol. For each input product, the cropland acreage in each unit is calculated as follows: 
$a_{i,j}=\sum _{m=1}^N(S_m\times P_m)$$a_{i,j}=\sum _{m=1}^N \left(S_m\times P_m\right)$a_(i,j)=sum_(m=1)^(N)(S_(m)xxP_(m))a_{i, j}=\sum_{m=1}^{N}\left(S_{m} \times P_{m}\right)
where $a_{i,j}$$a_{i,j}$a_(i,j)a_{i, j} denotes the cropland acreage of unit $j$$j$jj estimated by input product $i$$i$ii; $P_m$$P_m$P_(m)P_{m} denotes the cropland percentage in pixel $m$$m$mm after data processing; $S_m$$S_m$S_(m)S_{m} denotes the pixel area computed by equal-area projection; $m$$m$mm denotes the pixel labeled as cropland. Besides, absolute difference $A{D}_{i,j}$$A{D}_{i,j}$AD_(i,j)A D_{i, j} between the statistics and cropland acreage estimated from input product $i$$i$ii is computed to evaluate the accuracy of input maps. 
$A{D}_{i,j}=\mathrm{abs}\left(\frac{a_{{\mathrm{NBS}}_{j}j}-a_{i,j}}{a_{{\mathrm{NBS}}_{,j}}}\right)$$A{D}_{i,j}=\mathrm{abs}\left(\frac{a_{{\mathrm{NBS}}_{j}j}-a_{i,j}}{a_{{\mathrm{NBS}}_{,j}}}\right)$AD_(i,j)=abs((a_(NBS_(j)j)-a_(i,j))/(a_(NBS_(,j))))A D_{i, j}=\operatorname{abs}\left(\frac{a_{\mathrm{NBS}_{j} j}-a_{i, j}}{a_{\mathrm{NBS}_{, j}}}\right)
where $a_{\mathrm{NBS},j}$$a_{\mathrm{NBS},j}$a_(NBS,j)a_{\mathrm{NBS}, j} is the cropland acreage statistics of unit $j$$j$jj derived from NBS. A lower value of $A{D}_{i,j}$$A{D}_{i,j}$AD_(i,j)A D_{i, j} signifies finer agreement with the official statistics and a superior ranking for the input map. 

Protocol ranking scores are generated using tables that depict the agreement and ranking of the input product. When working with five input products, they are typically labeled as A, B, C, D, and E, ranked from highest to lowest. Agreement levels, ranging from 0 to 5 , represent the number of input products that identify a pixel as cropland. Since there are 32 permutations $(2^5=32)$$\left(2^5=32\right)$(2^(5)=32)\left(2^{5}=32\right) for five input products, the scores range from 0 to 31 (Table 3). A higher score indicates a higher likelihood of a pixel being cropland. An agreement level of 5 signifies that all input products classify the pixel as cropland, giving the pixel the highest score of 31. Conversely, an agreement level of 0 indicates that all the products categorize the pixel as non-cropland, resulting in the lowest score of 0. For other agreement levels, there are various permutations for the products. For instance, when the agreement level is 3, there are ten possible combinations with score values ranging from 16 to 25 . In scenarios where $\mathrm{A},\mathrm{B}$$\mathrm{A},\mathrm{B}$A,B\mathrm{A}, \mathrm{B}, and C have higher rankings, the score value is set as 25 if all three indicate cropland, which is higher than other combinations. By following these guidelines, values for a complete scoring table with five input products were determined, and these values were subsequently used to transform the input cropland layers into an agreement-ranking map. 

图 3 显示了五个输入产品的统计分配流程图。最初，选择了得分最高的 31 个像素，并计算了它们的总面积。
$A_{31}=\sum (S_{31,m}\times P_{31,m})$$A_{31}=\sum \left(S_{31,m}\times P_{31,m}\right)$A_(31)=sum(S_(31,m)xxP_(31,m))A_{31}=\sum\left(S_{31, m} \times P_{31, m}\right)
where $P_{31,m}$$P_{31,m}$P_(31,m)P_{31, m} and $S_{31,m}$$S_{31,m}$S_(31,m)S_{31, m} are the average percentage and pixel area of pixel $m$$m$mm labeled as the score 31 . If the acreage was far less than that the statistics, cropland pixels with the second-highest agreement rank, i.e., a score of 30 , were selected, and the total acreage was thenceforth computed. The cumulative cropland acres with scores of 30 and above were compared with the statistics. Pixels labeled with scores of 31 and 30 were designated as cropland pixels if the cumulative acreage was pretty close to the statistics, or else, pixels with lower scores were included until the accumulated acreage equaled the statistics. As sketched in Fig. 3, pixels with score values ranging from 29 to 31 were considered as cropland when the cumulative acreage with score of 29 was the closest to the statistics. By and large, the scoring values signaled the agreements among input products, reflecting the confidence level of cropland pixels. To standardize the scores to the same scale, a normalization process was adopted, resulting in confidence levels with values ranging from $0\mathrm{\%}$$0\mathrm{\%}$0%0 \% to $100\mathrm{\%}$$100\mathrm{\%}$100%100 \%. 

Based on the physical geographic zoning of the CAS, the study area was divided into seven parts, as shown in Fig. 4, to investigate regional disparities in the consistency of cropland datasets. Of these, the Northeast exhibited the highest percentage of complete agreement (65%), followed by East and Central China, both with rates exceeding 50%, whereas South and Southwest China had a lower agreement percentage, at around $20\mathrm{\%}$$20\mathrm{\%}$20%20 \% (Fig. $4a_1,b_1$$4a_1,b_1$4a_(1),b_(1)4 a_{1}, b_{1} and $c_1$$c_1$c_(1)c_{1} ). Horizontally, the Northeast accounted for approximately $30\mathrm{\%}$$30\mathrm{\%}$30%30 \% of the total, followed by East China, which represented more than $20\mathrm{\%}$$20\mathrm{\%}$20%20 \%, and South China, which contributed less than $5\mathrm{\%}$$5\mathrm{\%}$5%5 \%. Furthermore, the spatially consistent fractions at the provincial level posed variations across the years (Fig. $4a_2,b_2$$4a_2,b_2$4a_(2),b_(2)4 a_{2}, b_{2}, and $c_2$$c_2$c_(2)c_{2} ). In 2000, Heilongjiang, Henan, and Shandong provinces exhibited the highest agreement, constituting about $70\mathrm{\%}$$70\mathrm{\%}$70%70 \% of the total, while Tibet, Guizhou, and Fujian provinces had the worst agreement, comprising less than $10\mathrm{\%}$$10\mathrm{\%}$10%10 \%. By 2020, Heilongjiang and Jilin had the highest agreement, though their share had decreased. The spectral and textural features of cropland in satellite images were challenging to differentiate in regions 

Fig. 4d illustrates the variation in spatial consistency concerning elevation and slope for the five sets of cropland data. The ratio of high and full agreement was more pronounced in plains with elevations below 20 m and hilly areas between 20 and 200 m , indicating strong consistency among the datasets in these region. Consistency decreased with increasing altitude, with elevations ranging from 500 to 1500 m primarily found on the Mongolian Plateau, Tarim Basin, Loess Plateau, and Yunnan-Guizhou Plateau. These areas were characterized by mountainous terrain and fragmented topography, making cropland extraction challenging and resulting in a high level of inconsistency (37.5%). Higher altitudes above 1500 m were mainly situated in the northwestern Tibetan Plateau, exhibiting an inconsistency rate of up to $50.6\mathrm{\%}$$50.6\mathrm{\%}$50.6%50.6 \%. Similarly, slopes less than $2^{\circ }$$2^{\circ }$2^(@)2^{\circ} were primarily scattered across flat plains and basins with relatively simple geographical landscapes, suitable for agricultural cultivation. This led to better agreement in cropland extraction, with $20.1\mathrm{\%}$$20.1\mathrm{\%}$20.1%20.1 \% and $44.2\mathrm{\%}$$44.2\mathrm{\%}$44.2%44.2 \% showing high and complete agreement. In the slope range of $2-6^{\circ }$$2-6^{\circ }$2-6^(@)2-6^{\circ}, the proportion of inconsistency increased to $22.9\mathrm{\%}$$22.9\mathrm{\%}$22.9%22.9 \%, while complete consistency decreased to $19.4\mathrm{\%}$$19.4\mathrm{\%}$19.4%19.4 \%. Slopes of $15-{25}^{\circ }$$15-{25}^{\circ }$15-25^(@)15-25^{\circ} and above were chiefly distributed in the Qinghai-Tibet Plateau and its periphery, with inconsistency accounting for $58.5\mathrm{\%}$$58.5\mathrm{\%}$58.5%58.5 \% and $74.0\mathrm{\%}$$74.0\mathrm{\%}$74.0%74.0 \%, respectively. Overall, the accuracy of land cover classification in 
the Southwest, Northwest, and South China, where terrain slope was significant, was heavily influenced by relief and roughness. However, when relief and roughness reached a certain level, the land cover type became relatively simple and mainly non-cropland due to its unsuitability for human exploitation (Zhang et al., 2015). This stability in land cover classification agreement resulted from the land’s limited suitability for agricultural use. 

Fig. 5a shows the deviation between the cropland acreage retrieved from the five datasets and the statistics. The estimated cropland ratio for each data product was distinct and overestimated or underestimated to varying degrees for the most part. Specifically, the CLCD underestimated cropland acreage in the Northeast, Northwest, and North China by $4.0\mathrm{\%}$$4.0\mathrm{\%}$4.0%4.0 \%, $2.1\mathrm{\%}$$2.1\mathrm{\%}$2.1%2.1 \%, and $2.0\mathrm{\%}$$2.0\mathrm{\%}$2.0%2.0 \%, respectively, while the estimates for Central and South China were relatively consistent. GLC_FCS30 also underestimated cropland in Northeast and North China by $4.4\mathrm{\%}$$4.4\mathrm{\%}$4.4%4.4 \% and $2.8\mathrm{\%}$$2.8\mathrm{\%}$2.8%2.8 \% but overestimated it by $3.3\mathrm{\%},2.1\mathrm{\%}$$3.3\mathrm{\%},2.1\mathrm{\%}$3.3%,2.1%3.3 \%, 2.1 \%, and $2.6\mathrm{\%}$$2.6\mathrm{\%}$2.6%2.6 \% in East, Central, and South China, which broadly aligned with the statistics for the Northwest. Globeland30 exhibited a bias of approximately $5.9\mathrm{\%}$$5.9\mathrm{\%}$5.9%5.9 \% and $3.1\mathrm{\%}$$3.1\mathrm{\%}$3.1%3.1 \% in its estimates of cropland in Northeast and North China, in line with the statistics for Central China. GlobalCrop overestimated cropland in Northeast and East China by $2.1\mathrm{\%}$$2.1\mathrm{\%}$2.1%2.1 \% and $2.6\mathrm{\%}$$2.6\mathrm{\%}$2.6%2.6 \% while undervaluing it in Southwest and South China. In East, Central, and South China, ESA_CCI’s estimated cropland area was $3.8\mathrm{\%},2.0\mathrm{\%}$$3.8\mathrm{\%},2.0\mathrm{\%}$3.8%,2.0%3.8 \%, 2.0 \%, and $2.6\mathrm{\%}$$2.6\mathrm{\%}$2.6%2.6 \% higher than the statistical data, while there was a significant underestimation in Northeast and North China, with biases of $3.5\mathrm{\%}$$3.5\mathrm{\%}$3.5%3.5 \% and $4.5\mathrm{\%}$$4.5\mathrm{\%}$4.5%4.5 \%, respectively. Fig. 5b presents the overall accuracy estimates, using an error matrix based on training samples in each district. In North and Northeast China, GlobalCrop achieved the highest overall accuracy ( $84.0\mathrm{\%}$$84.0\mathrm{\%}$84.0%84.0 \% and $85.1\mathrm{\%}$$85.1\mathrm{\%}$85.1%85.1 \% ). In Central and South China, CLCD achieved the highest accuracy ( $89.5\mathrm{\%}$$89.5\mathrm{\%}$89.5%89.5 \% and $87.7\mathrm{\%}$$87.7\mathrm{\%}$87.7%87.7 \% ), and Globeland30 performed exceptionally well in the northwest with an overall accuracy of $86.1\mathrm{\%}$$86.1\mathrm{\%}$86.1%86.1 \%. These input mapping datasets were ranked in each district to create the corresponding scoring sheet based on overall accuracy. 

Fig. 7 presents the relationship between the percentage of cropland acreage derived from agricultural statistics and the estimates obtained from the province-by-province cropland datasets. A comparison of these individual cropland datasets reveals that the synergy maps exhibit the highest level of agreement with the statistics, with the lowest RMSE (Root Mean Square Error) of $0.21\mathrm{\%}$$0.21\mathrm{\%}$0.21%0.21 \% and a high correlation coefficient $\left(R^2\right)$$\left(R^2\right)$(R^(2))\left(R^{2}\right) of 0.97 . It is worth noting that CLCD achieved a superior $R^2(0.93)$$R^2(0.93)$R^(2)(0.93)R^{2}(0.93) and a lower RMSE ( $0.68\mathrm{\%}$$0.68\mathrm{\%}$0.68%0.68 \% ) compared to the other four datasets. This could be attributed to the fact that CLCD’s classification results are more closely related to China compared to other global land cover mappings. In contrast, the data points for GlobalCrop noticeably deviate from the 1:1 line, with a higher RMSE ( $0.81\mathrm{\%}$$0.81\mathrm{\%}$0.81%0.81 \% ) and a lower $R^2$$R^2$R^(2)R^{2} ( 0.86 ). This divergence may be attributed to GlobalCrop’s definition of cropland, which includes various mosaic types. For instance, GlobalCrop encompasses land used for planting year-round and perennial herbaceous crops for feed, biofuels, and human consumption (Potapov et al., 2021). The presence of mixed pixels resulting from fragmented landscape patches leads to variations in classifications and discrepancies in cropland area estimates across different products and in comparison to the statistics. In summary, the synergy maps exhibit better agreement with the statistics, demonstrating the effectiveness of this approach in tackling inconsistencies between satellite-based cropland maps and departmental statistics. 

Table 4 lists the accuracy evaluation results for the five cropland datasets and their synergy maps within the training sample zone. GlobalCrop exhibited the highest spatial location reliability among these input datasets, achieving a Kappa coefficient of 0.64 and an overall accuracy of $87.7\mathrm{\%}$$87.7\mathrm{\%}$87.7%87.7 \%. CLCD and GlobeLand30 followed closely with overall accuracies of $86.1\mathrm{\%}$$86.1\mathrm{\%}$86.1%86.1 \% and $85.6\mathrm{\%}$$85.6\mathrm{\%}$85.6%85.6 \%, and Kappa coefficients of 0.64 and 0.63 , respectively. In contrast, ESA_CCI and GLC_FCS30 demonstrated lower positional reliability, with overall accuracies of $84.1\mathrm{\%}$$84.1\mathrm{\%}$84.1%84.1 \% and $84.0\mathrm{\%}$$84.0\mathrm{\%}$84.0%84.0 \%, and Kappa coefficients of 0.59 and 0.60 , respectively. Specifically, CLCD exhibited a misclassification rate of $34.6\mathrm{\%}$$34.6\mathrm{\%}$34.6%34.6 \% and an omission 

Fig. 6. Synergy outcomes based on five cropland mapping datasets: (a) average cropland percentage; (b) optimal agreement level; © cropland percentage map; (d) cropland confidence map. 

Fig. 7. Scatterplots of cropland percentage from statistics and those estimated by CLCD (a); GLC_FCS30 (b); Globeland30 ©; GlobalCrop (d); ESA_CCI (e) and synergy map ( f ). 

$17.6\mathrm{\%}$$17.6\mathrm{\%}$17.6%17.6 \% 的比率，主要在西南和东北地区（图 8a）。GLC_FCS30 的误分类率较高（39.13%），但遗漏率较低 $(17.3\mathrm{\%})$$(17.3\mathrm{\%})$(17.3%)(17.3 \%) ，大多数遗漏的耕地集中在西北。GLC_FCS30 中耕地的高误分类率可能归因于将东南部的大块花园和林地错误分类为耕地。GlobeLand30 显示出最低的耕地遗漏率，但误分类率较高，错误标记的耕地

图 8. 样本区域内漏标耕地和错误标记耕地的空间分布。
predominantly in southwest China (Fig. 8c). GlobalCrop exhibited the lowest rate of cropland misclassification but a higher rate of omission, mostly in western China (Fig. 8d). Additionally, ESA_CCI had a cropland commission rate of $38.2\mathrm{\%}$$38.2\mathrm{\%}$38.2%38.2 \% and a cropland omission rate of $21.6\mathrm{\%}$$21.6\mathrm{\%}$21.6%21.6 \% 

（图 8e），均低于 GLC_FCS30 和 GlobalCrop。这表明，当采用合适的技术时，低空间分辨率数据也可以实现正确的分类。协同耕地地图的准确性是通过误差矩阵进行评估的。

图 9. 2000-2020 年中国耕地的时空动态分布。
validation samples (Fig. 8f), and the validation results are presented in Table 4. The overall accuracy of the synergistic maps reached $93.3\mathrm{\%}$$93.3\mathrm{\%}$93.3%93.3 \%, with a Kappa coefficient of 0.82 . The commission rate and omission rate for cropland were $12.9\mathrm{\%}$$12.9\mathrm{\%}$12.9%12.9 \% and $7.8\mathrm{\%}$$7.8\mathrm{\%}$7.8%7.8 \%, both lower than those observed for the individual datasets mentioned earlier. This indicates that the synergistic approach can harness multiple datasets to create more accurate hybrid maps. The enhanced overall accuracy of SOSA reflects the feasibility and traceability of the fusion method employed in these experiments and signifies the successful integration of multi-source cropland data into a newly refined dataset with scientifically improved features. 

Spatial analysis of input products and their synergy maps was employed to discern the evolving features and patterns of China’s cropland at the raster level (Fig. 9). The overall cropland distribution has remained relatively stable over the past two decades, with dynamics characterized by regional variations and subtle shifts. On a macroscopic scale, the center of cropland gravity has shifted towards the northwest and northeast, accelerated by the decline of high-quality arable land in the south, where water and temperature conditions are better suited for other land uses. On a micro scale, this shift is reflected in the reallocation of cropland resources between urban and rural areas, as well as the reclamation of sloped wasteland to expand cropland area. The total cropland area continued to decline rapidly until 2005, with an annual decrease of 278,000 ha. Factors contributing to this decline included ecological reclamation, land occupation for construction, damage from natural disasters, and agricultural restructuring (Duan et al., 2021). Subsequently, the central government implemented a series of stringent measures and protection systems. High-quality cropland was established, and local governments were held responsible for maintaining the cropland area and the protected basic farmland within their administrative districts, as outlined in the current territorial spatial planning. Specific policies included the demarcation of redlines for cropland, the abolition of agricultural taxes, and the establishment of a permanent mechanism for the protection of basic farmland (Tian et al., 2021). These measures have to some extent effectively curbed the trend of cropland reduction resulting from land misuse or unlawful appropriation. However, the decrease in cropland area between 2010 and 2020, despite stringent countermeasures against non-agricultural land encroachment, was due to land greening efforts and agricultural restructuring (Hu et al., 2020). With the deepening of conservation policies, continuous improvements and enhancements in land management models, methods, and technical measures, and the rigorous implementation of protection systems such as cropland balance (Zhong et al., 2022), China’s total cropland area has generally maintained a dynamic equilibrium. 

Regarding the shift of cropland within each province (Fig. 10), it was observed that $70.9\mathrm{\%}$$70.9\mathrm{\%}$70.9%70.9 \% of provinces experienced a decrease in cropland area during the study period. Notably, Shandong, Henan, Jiangsu, Sichuan, and Hebei provinces exhibited a significant decline. These provinces are characterized by extensive agriculture and high population density, but they face challenges such as low per capita cropland availability and limited reserve resources. Recent urban expansion has resulted in increased agricultural land expropriation, intensifying the risk of cropland loss. Furthermore, anthropogenic cropland abandonment, ecological reclamation efforts, and disaster-related damage have compounded the difficulties of preserving local cropland (Zeng et al., 2023). In contrast, Xinjiang, Heilongjiang, Inner Mongolia, Shanxi, and Ningxia provinces witnessed a substantial increase in cropland area. Xinjiang, in particular, added 3.19 million hectares of cropland, which accounted for approximately $40\mathrm{\%}$$40\mathrm{\%}$40%40 \% of the country’s total increase. Inner Mongolia and Heilongjiang also contributed significantly, with more than $25\mathrm{\%}$$25\mathrm{\%}$25%25 \% and $15\mathrm{\%}$$15\mathrm{\%}$15%15 \% of the total increase, respectively. These provinces, with significant influence over China’s cropland changes, have gradually achieved a balance between reducing and expanding cropland. This has been made possible through improved irrigation and water conservation infrastructure, increased investment in agricultural technology, large-scale land revitalization efforts, and pilot programs for cropland rotation. These initiatives have played a pivotal role in maintaining overall cropland stability across the country. 

Significantly, scoring assignment played a pivotal role in determining combinations of remotely sensed map products. SOSA streamlined the scoring method, eliminating the need for training samples, which sets it apart from other harmonized methods. Previous approaches involved the creation of extensive static score sheets to distinguish cropland from non-cropland, with $2^n$$2^n$2^(n)2^{n} possible score combinations for $n$$n$nn input products, making the process time-consuming and 

Bcijing (BD); Tianjin (TJ); Hebci (HEB); Shanxi (SX); Inner Mongolia (IM); Liaoning (LN); Jilin (JL); Heilongiang (HLJ); Shanghai (SH); Jiangsu (JS); Zhejiang (ZJ); Anhui $(\mathrm{AH});$$(\mathrm{AH});$(AH);(\mathrm{AH}) ; Fujian (FJ); Jiangxi (JX); Shandong (SD); Henan (HEN); Hubei (HUB); Hunan (HUN); Guangdong (GD); Guangxi (GX); Hainan $(\mathrm{HN})$$(\mathrm{HN})$(HN)(\mathrm{HN}); Chongqing $(\mathrm{CQ})$$(\mathrm{CQ})$(CQ)(\mathrm{CQ}); Sichuan $(\mathrm{SC})$$(\mathrm{SC})$(SC)(\mathrm{SC}); Guizhou $(\mathrm{GZ})$$(\mathrm{GZ})$(GZ)(\mathrm{GZ}); Yunnan $(\mathrm{YN})$$(\mathrm{YN})$(YN)(\mathrm{YN}); Tibet $(\mathrm{TB})$$(\mathrm{TB})$(TB)(\mathrm{TB}); Shannxi $(\mathrm{SHX})$$(\mathrm{SHX})$(SHX)(\mathrm{SHX}); Gansu (GS); Qinghai $(\mathrm{QH})$$(\mathrm{QH})$(QH)(\mathrm{QH}); Ningxia (NX); Xinjiang $(\mathrm{XI})$$(\mathrm{XI})$(XI)(\mathrm{XI}) 

Our study combines existing global land cover products synergistically to enhance the accuracy of Chinese cropland estimates. This approach is well-suited to reduce local discrepancies between remote sensing data and national cropland statistics. We introduce a new calibration method based on remote sensing images and statistics and validate the resulting cropland map. This method has significant potential to streamline the process of achieving dataset synergies compared to conventional scoring assignment methods. It is also adaptable, allowing for the seamless integration of new products as they become available. Initial evidence and comparisons demonstrate that the synergistic maps exhibit higher accuracy and better statistical consistency than the original individual mapping products. Furthermore, this approach can be extended beyond its current focus on cropland mapping to cover entire continents and even global scales. It is applicable to a wide variety of land cover types, including forests, grasslands, and water bodies. However, our evaluation also suggests that there is still room for improvement, as the method described here heavily relies on the accuracy and coverage of the input layer, as well as the reliability of sub-national statistics. This mapping is expected to be further refined as more high-quality data becomes available in the foreseeable future. 

Akpoti, K., Kabo-bah, A., & Zwart, S. (2019). 农业用地适宜性分析：最新进展及气候变化分析整合的展望。《农业系统》，173，172-208。

贝克-雷谢夫, I., 贾斯蒂斯, C., 巴克, B., 汉伯, M., 伦博尔德, F., 博尼法西奥, R., 扎帕科斯塔, M., 布德, M., 马加兹迪雷, T., & 希托特, C. (2020). 加强面临粮食不安全风险国家的农业决策：GEOGLAM 作物监测早期预警系统. 环境遥感, 237, 文章 111553.

Benhammou, Y., Alcaraz-Segura, D., Guirado, E., Khaldi, R., Achchab, B., Herrera, F., & Tabik, S. (2022). Sentinel2GlobalLULC：一个用于全球土地利用/覆盖制图的哨兵-2 RGB 图像切片数据集，结合深度学习。科学数据，9，681。

Brovelli, M., Molinari, M., Hussein, E., Chen, J., & Li, R. (2015). 全球土地 30 的首次国家级全面精度评估：方法论与结果。遥感, 7, 4197-4212。

陈, D., 陆, M., 周, Q., 肖, J., 汝, Y., 魏, Y., & 吴, W. (2019). 两种协同方法在混合农田制图中的比较. 遥感, 11(3), 213.

陈华，谭勇，肖伟，何涛，徐晟，孟飞，李晓，熊伟。（2023）。中国过去 20 年补充耕地利用的连续性和效率评估：耕地废弃的视角。《清洁生产杂志》，388，文章 135987。

Claverie, M., Vermote, E., Weiss, M., Baret, F., Hagolle, O., & Demarez, V. (2013) 在法国西南部农田上验证粗空间分辨率的 LAI 和 FAPAR 时间序列。环境遥感, 139, 216-230.

Crane-Droesch, A. (2018). 农业中作物产量预测和气候变化影响评估的机器学习方法。环境研究快报, 13, 文章 114003。

段杰，任超，王思，张晓，雷斯，徐静，顾斌。（2021）。农业用地的整合可以促进中国的农业可持续性。《自然食品》，2，1014-1022。

Duro, J., Lauk, C., Kastner, T., Erb, K., & Haberl, H. (2020). 全球食品消费、耕地需求和土地利用效率的不平等：一项分解分析。全球环境变化, 64, 文章 102124。

弗里茨, S., 西, L., 你, L., 贾斯蒂斯, C., 贝克-雷谢夫, I., 比德克尔克, L., 库马尼, R., 德福尔尼, P., 埃尔布, K., 福利, J., & 吉利亚姆斯, S. (2013). 需要改进全球农田地图. Eos, 美国地球物理联盟会刊, 94, 31-32.

Fritz, S., You, L., Bun, A., See, L., McCallum, I., Schill, C., Perger, C., Liu, J., Hansen, M., & Obersteiner, M. (2011). 撒哈拉以南非洲的农田：使用五个土地覆盖数据集的协同方法。地球物理研究快报, 38, 文章 L04404。
Gumma, M., Thenkabail, P., Teluguntla, P., Oliphant, A., Xiong, J., Giri, C., Pyla, V., Dixit, S., & Whitbread, A. (2020). Agricultural cropland extent and areas of South Asia derived using Landsatsatellite $30-\mathrm{m}$$30-\mathrm{m}$30-m30-\mathrm{m} time-series big-data using random forest machine learningalgorithms on the Google Earth Engine cloud. GIScience and Remote Sensing, 57, 302-322. 

韩志，宋伟。（2020）。废弃农田：广西喀斯特山区的模式与决定因素。《应用地理》，122，文章 102245。

哈特菲尔德，J.，安特尔，J.，加雷特，K.，伊萨乌拉尔德，R.，马德，T.，马歇尔，E.，尼亚林，M.，罗伯逊，P.，& 齐斯卡，L.（2018）。农业系统中的气候变化指标。《气候变化》，163，1719-1732。

黄, J., Tichit, M., Poulot, M., Darly, S., Li, S., Petit, C., & Aubry, C. (2015). 可持续农业中多功能性和生态系统服务的比较评审. 环境管理杂志, 149, 138-147.

华, T., 赵, W., 刘, Y., 王, S., & 杨, S. (2018). 全球土地覆盖数据集的空间一致性评估：GLC2000、CCI LC、MCD12、GLOBCOVER 和 GLCNMO 之间的比较. 遥感, 10(11), 1846.

胡, Q., 向, M., 陈, D., 周, J., 吴, W., & 宋, Q. (2020). 2000 年至 2010 年全球耕地集约化超过扩张：基于 GlobeLand30 的时空分析. 《环境科学总论》，746，文章 141035.

刘, X., 巴克希, B., 鲁甘尼, B., 索萨, D., 巴雷, J., 约翰斯顿, J., 拉伦特, A., & 维罗内斯, F. (2020). 生态系统服务在生命周期评估中的量化与评估：级联框架在稻米种植系统中的应用. 《环境科学总论》，747，文章 141278.

刘涛, 刘华, & 齐勇. (2015). 城市化中国的建设用地扩张与耕地保护：来自 1996-2006 年全国土地调查的见解. 国际栖息地, 46, 13-22.
Liu, Y., Sun, D., Wang, H., Wang, X., Yu, G., & Zhao, X. (2020). An evaluation of China’s agricultural green production: 1978-2017. Journal of Cleaner Production, 243, Article 118483.