高分辨率土壤湿度估算对于规划水管理和评估环境质量至关重要。仅现场测量成本太高,无法支持水管理所需的空间和时间分辨率。最近的努力将校准数据与机器学习算法相结合,以填补现场缺乏高分辨率水分估计的空白。本研究旨在提供校准的土壤湿度模型和方法,以生成多个深度的土壤湿度的网格估计,根据用户定义的时间段,空间分辨率和范围。
我们应用了来自100多个站点的近100万个国家图书馆土壤湿度记录,横跨美国中西部和西部,建立分位数随机森林(QRF)校准模型。QRF模型建立在协变量上,包括来自北美土地数据同化系统(NLDAS)的土壤湿度估计,土壤性质,气候变量,数字高程模型,和遥感衍生指数。我们还探索了一种替代方法,该方法采用了美国西部地区的区域化校准数据集。根据采样深度独立验证了广泛的QRF模型。土地覆盖类型,和观察期。然后,我们探索了使用用于加标的局部样本改进的模型性能。最后,QRF模型用于在田间尺度上估算土壤水分,并进行评估以检查估计的时间和空间模式。
当考虑来自所有深度层(高达100cm)的数据点进行独立验证时,宽尺度QRF模型显示出中等性能(R2=0.53,RMSE=0.078m3/m3)。立面图,NLDAS衍生的水分,土壤性质,和采样深度被列为最重要的协变量。森林和牧场的最佳模型性能(R2>0.5;RMSE<0.09m3/m3),其次是草地和农田(R2>0.4;RMSE<0.11m3/m3)。模型性能随采样深度而下降,在冬季则略低。通过将草地站点的RMSE降低到小于0.05m3/m3,在国家QRF模型中添加本地样品可以改善模型性能。在现场尺度上,模型估计显示了地表比地下土壤层更准确的时间趋势。模型估计的空间模式需要进一步改进,并通过管理数据进行验证。
顶部0-20cm土壤深度(R2>0.5,RMSE<0.08m3/m3)的模型精度显示出采用土壤水分监测方法的希望。用当地样本对国家模型进行加标的成功表明,需要收集多年的高频率(例如,每小时)基于传感器的现场测量,以改善更长时间段内土壤湿度的估计。未来的工作应该通过额外的水力特性和使用本地选择的校准数据集,提高更深深度的模型性能。
High-resolution soil moisture estimates are critical for planning water management and assessing environmental quality. In-situ measurements alone are too costly to support the spatial and temporal resolutions needed for water management. Recent efforts have combined calibration data with machine learning algorithms to fill the gap where high resolution moisture estimates are lacking at the field scale. This study aimed to provide calibrated soil moisture models and methodology for generating gridded estimates of soil moisture at multiple depths, according to user-defined temporal periods, spatial resolution and extent.
We applied nearly one million national library soil moisture records from over 100 sites, spanning the U.S. Midwest and West, to build Quantile Random Forest (QRF) calibration models. The QRF models were built on covariates including soil moisture estimates from North American Land Data Assimilation System (NLDAS), soil properties, climate variables, digital elevation models, and remote sensing-derived indices. We also explored an alternative approach that adopted a regionalized calibration dataset for the Western U.S. The broad-scale QRF models were independently validated according to sampling depths, land cover type, and observation period. We then explored the model performance improved with local samples used for
spiking. Finally, the QRF models were applied to estimate soil moisture at the field scale where evaluation was carried out to check estimated temporal and spatial patterns.
The broad-scale QRF model showed moderate performance (R2 = 0.53, RMSE = 0.078 m3/m3) when data points from all depth layers (up to 100 cm) were considered for an independent validation. Elevation, NLDAS-derived moisture, soil properties, and sampling depth were ranked as the most important covariates. The best model performance was observed for forest and pasture sites (R2 > 0.5; RMSE < 0.09 m3/m3), followed by grassland and cropland (R2 > 0.4; RMSE < 0.11 m3/m3). Model performance decreased with sampling depths and was slightly lower during the winter months.
Spiking the national QRF model with local samples improved model performance by reducing the RMSE to less than 0.05 m3/m3 for grassland sites. At the field scale, model estimates illustrated more accurate temporal trends for surface than subsurface soil layers. Model estimated spatial patterns need to be further improved and validated with management data.
The model accuracy for top 0-20 cm soil depth (R2 > 0.5, RMSE < 0.08 m3/m3) showed promise for adopting the methodology for soil moisture monitoring. The success of
spiking the national model with local samples showed the need to collect multi-year high frequency (e.g., hourly) sensor-based field measurements to improve estimates of soil moisture for a longer time period. Future work should improve model performance for deeper depths with additional hydraulic properties and use of locally-selected calibration datasets.