Fractional Abundance Datasets for Salt Patch and Marshland Across the Delmarva Peninsula, v2

Abstract: Coastal agricultural lands in the eastern USA are increasingly plagued by escalating soil salinity, rendering them unsuitable for profitable farming. Increasing soil salinization can lead to both land cover modification and conversion. Two notable instances of such transformations include the conversion of farmland to marshland or to barren salt patches devoid of vegetation. However, quantifying these land cover changes across large geographic regions poses a significant challenge due to their varying spatial granularity. To tackle this issue, we first developed a machine-learning based method using Sentinel-2 imagery for 2022 where we used a non-linear spectral unmixing approach utilizing a Random Forest (RF) algorithm (Sarupria et al., 2025). The RF models were constructed using 100 trees and 27,437 reference data points, resulting in two sets of ten models: one for salt patches and another for marshland. Validation metrics for sub-pixel fractional abundances revealed a moderate R-squared value of 0.50 for the salt model ensemble and a high R-squared value of 0.90 for the marsh model ensemble. Building upon this methodology, we then generated annual gridded datasets of fractional abundance for salt patch and marshland across the Delmarva Peninsula (14 coastal counties in Delaware, Maryland and Virginia, USA) for 2019-2023. In these datasets, we only report mean fractional abundance values ranging from 0.4 to 1 for salt patches and 0.25 to 1 for marshland, along with the standard deviation associated with each value. Description: This data collection consists of 20 single-band raster files: fractional abundance mean values and associated standard deviation values for two land covers, salt patch and marshland, produced annually over the five-year period. Salt Patch Fractional Abundance Mean (2019–2023): Five files, each representing the per-pixel fractional abundance mean of salt patches for the years 2019–2023. Values are derived from an ensemble of 10 Random Forest (RF) models. Only pixels with a salt patch fraction ≥ 0.40 were retained. Salt Patch Fractional Abundance Standard Deviation (2019–2023): Five files representing the per-pixel standard deviation of the salt patch fractional abundance means for the years 2019–2023. Estimates are based on an ensemble of 10 RF models and include only pixels with a salt patch fraction ≥ 0.40. Marsh Fractional Abundance Mean (2019–2023): Five files, each showing the per-pixel fractional abundance mean of marshland for the years 2019–2023, derived from an ensemble of 10 RF models. Only pixels with a marsh fraction ≥ 0.25 were retained. Marsh Fractional Abundance Standard Deviation (2019–2023): Five files showing the per-pixel standard deviation of the marsh fractional abundance means for 2019–2023. Estimates are based on an ensemble of 10 RF models, limited to pixels with a marsh fraction ≥ 0.25. Input Data: This approach integrated Sentinel-2 surface reflectance imagery, a global land use/land cover dataset from ESRI (Karra et al., 2021), a NAIP-derived Delmarva land cover dataset (Mondal et al., 2022), high-resolution PlanetScope true color images (Planet Team, 2017), very high-resolution Unoccupied Aerial Vehicle (UAV) imagery, and ground truth data. More details on input data can be found in Sarupria et al., 2025a and version 1 of this dataset (Sarupria et al., 2025b). Method: We utilized Sentinel-2 Level 2 A surface reflectance imagery for spectral unmixing. This multispectral dataset, corrected for atmospheric and radiometric effects, encompasses 13 spectral bands from visible to near-infrared wavelengths (0.443–2.190 micrometers). The imagery offers spatial resolutions ranging from 10 m to 60 m and is captured every 5 days. To aid in selecting reference points for model training and testing, high-resolution (60 cm) UAV images of specific farmlands in Dorchester and Somerset counties, Maryland, were acquired under optimal weather conditions. The study incorporated multiple datasets to refine the analysis. The Sentinel-2 derived global land use/land cover dataset from ESRI was employed to isolate relevant land cover classes such as 'Crops' and 'Rangeland'. A NAIP-derived Delmarva land cover dataset with eight classes helped exclude non-agricultural land cover types. High-resolution PlanetScope true color images with 3 m spatial resolution were used as reference data for model validation. In this study, we applied a Random Forest (RF) classifier for nonlinear spectral unmixing. The RF classifier functions by utilizing an ensemble of decision trees that are independently trained on random subsets of training data through bootstrap aggregation. The final classification is determined by aggregating votes from all trees, with the endmember receiving the highest total votes being selected as the final output. To access soft voting information from the RF classifier in python, we used its probability prediction function called ‘predict_proba’. This function enables each decision tree to produce a probability distribution for each endmember instead of making a single class decision. The probability distribution from a decision tree indicates how likely it is that an input pixel belongs to each endmember. The final predicted probabilities are calculated by averaging these distributions across all decision trees for each of the five endmembers. As a result, each pixel in the final output is represented by five probability values that indicate the fractional abundance of each corresponding endmember within that pixel. These probabilities sum to one, effectively illustrating the spectral unmixing of a mixed pixel. For a specific endmember, a pixel with fractional abundance value of 0 signifies the absence of it, while a value of 1 indicates a pure pixel. Values between 0 and 1 reflect varying levels of mixed endmembers. More details on the methods and accuracy assessment can be found in Sarupria et al., 2025a. Data format: The spatial resolution of all the derived datasets is 10 m. These georeferenced datasets are distributed in GEOTIFF format and are compatible with GIS and/or image processing software, such as R and ArcGIS Pro. The GIS-ready raster files can be used directly in mapping and geospatial analysis. Code: Sample python code for performing spectral unmixing is available at: https://github.com/Manan-prog/Non-linear-Spectral-Unmixing. To run this code successfully, the user must provide training data for the desired land cover classes and an input raster image for spectral unmixing. Datasets for download: Five layers for salt patch mean values for 2019-2023: SaltPatch_FrAb_Mean_<Year> Five layers for salt patch standard deviation values for 2019-2023: SaltPatch_FrAb_StdDev_<Year> Five layers for marsh mean values for 2019-2023: Marsh_FrAb_Mean_<Year> Five layers for marsh standard deviation values for 2019-2023: Marsh_FrAb_StdDev_<Year>摘要： 美国东部沿海农业用地正日益遭受不断加剧的土壤盐渍化困扰，已无法开展盈利性耕作。土壤盐渍化程度加重可引发土地覆被改造与转换两类变化，其中典型的两种转换场景为农田转变为沼泽地，或是变为无植被覆盖的贫瘠盐渍斑块。然而，由于此类土地覆被变化的空间粒度存在差异，在大地理区域内对其进行量化仍面临严峻挑战。为解决这一问题，本研究首先基于2022年的Sentinel-2影像（Sentinel-2）开发了一种机器学习方法，采用随机森林（Random Forest）算法实现非线性光谱解混（non-linear spectral unmixing）（Sarupria等，2025）。该RF模型基于100棵决策树与27437个参考数据点构建，最终生成两组各含10个模型的集成模型：一组用于盐渍斑块识别，另一组用于沼泽地识别。亚像素分数丰度的验证结果显示，盐渍斑块模型集成的决定系数R²为0.50（中等水平），沼泽地模型集成的R²达0.90（高水平）。基于该方法，本研究进一步生成了2019-2023年德尔马瓦半岛（美国特拉华州、马里兰州及弗吉尼亚州的14个沿海县）范围内盐渍斑块与沼泽地的年度格网分数丰度数据集。本数据集仅报告盐渍斑块分数丰度范围为0.4~1的平均值，以及沼泽地分数丰度范围为0.25~1的平均值，并附带各值对应的标准差。 数据集描述： 本数据集包含20个单波段栅格文件，涵盖2019-2023年五年间每年生成的两种土地覆被（盐渍斑块、沼泽地）的分数丰度平均值及对应标准差。 盐渍斑块分数丰度平均值（2019-2023）：共5个文件，分别对应2019至2023年各年份盐渍斑块的逐像素分数丰度平均值。该数据由10个RF模型集成生成，仅保留盐渍斑块分数≥0.40的像素。 盐渍斑块分数丰度标准差（2019-2023）：共5个文件，分别对应2019至2023年各年份盐渍斑块分数丰度平均值的逐像素标准差。该估算基于10个RF模型集成，仅保留盐渍斑块分数≥0.40的像素。 沼泽地分数丰度平均值（2019-2023）：共5个文件，分别对应2019至2023年各年份沼泽地的逐像素分数丰度平均值，由10个RF模型集成生成，仅保留沼泽地分数≥0.25的像素。 沼泽地分数丰度标准差（2019-2023）：共5个文件，分别对应2019至2023年各年份沼泽地分数丰度平均值的逐像素标准差。该估算基于10个RF模型集成，仅保留沼泽地分数≥0.25的像素。 输入数据： 本方法整合了以下多源数据：Sentinel-2地表反射率影像（Sentinel-2）、ESRI发布的全球土地利用/土地覆被数据集（Karra等，2021）、基于NAIP生成的德尔马瓦半岛土地覆被数据集（Mondal等，2022）、高分辨率PlanetScope真彩色影像（Planet团队，2017）、超高分辨率无人飞行器（Unoccupied Aerial Vehicle, UAV）影像以及地面实测数据。 关于输入数据的更多细节可参见Sarupria等，2025a以及本数据集V1版本（Sarupria等，2025b）。 研究方法： 本研究采用Sentinel-2 Level 2A地表反射率影像开展光谱解混。该多光谱数据集经过大气与辐射校正，包含可见光至近红外波段共13个光谱通道（0.443~2.190微米），空间分辨率覆盖10米至60米，重访周期为5天。 为辅助选取模型训练与测试的参考点，本研究在最优气象条件下获取了美国马里兰州多切斯特县与萨默塞特县特定农田的超高分辨率（60厘米）UAV影像。 本研究整合多源数据集以优化分析流程：采用ESRI基于Sentinel-2生成的全球土地利用/土地覆被数据集，筛选出“农作物”“牧场”等相关土地覆被类别；使用基于NAIP生成的8类德尔马瓦半岛土地覆被数据集，排除非农业土地覆被类型；采用空间分辨率3米的高分辨率PlanetScope真彩色影像作为模型验证的参考数据。 本研究采用随机森林（Random Forest）分类器实现非线性光谱解混。RF分类器的工作原理为：通过bootstrap聚合（bootstrap aggregation）方法，基于训练数据的随机子集独立训练多个决策树，最终通过整合所有决策树的投票结果完成分类，得票最高的端元即为最终分类结果。为在Python中获取RF分类器的软投票信息，本研究使用了其`predict_proba`概率预测函数。该函数可使每个决策树输出每个端元的概率分布，而非仅输出单一分类结果。决策树输出的概率分布表示输入像素属于各端元的可能性。最终预测概率通过对5个端元各自的所有决策树概率分布取平均得到。因此，最终输出的每个像素由5个概率值表征，分别代表该像素内各对应端元的分数丰度，所有概率值之和为1，直观展示了混合像元的光谱解混结果。对于特定端元，分数丰度为0表示该端元在像素中不存在，为1表示该像素为纯端元像素，0~1之间的值则反映了混合像元中端元的占比水平。 关于本研究方法与精度评估的更多细节可参见Sarupria等，2025a。 数据格式： 所有衍生数据集的空间分辨率均为10米。这些带地理坐标的数据集以GEOTIFF格式（GEOTIFF）分发，可兼容GIS及图像处理软件（如R、ArcGIS Pro）。该类适配GIS的栅格文件可直接用于制图与地理空间分析。 代码： 用于执行光谱解混的Python示例代码可在以下网址获取：https://github.com/Manan-prog/Non-linear-Spectral-Unmixing。若要成功运行该代码，用户需提供目标土地覆被类别的训练数据以及用于光谱解混的输入栅格影像。 可供下载的数据集： 2019-2023年盐渍斑块平均值数据集（共5层）：SaltPatch_FrAb_Mean_<Year> 2019-2023年盐渍斑块标准差数据集（共5层）：SaltPatch_FrAb_StdDev_<Year> 2019-2023年沼泽地平均值数据集（共5层）：Marsh_FrAb_Mean_<Year> 2019-2023年沼泽地标准差数据集（共5层）：Marsh_FrAb_StdDev_<Year>