Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision

Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.

空间预测是基于所收集的地理空间数据，对任意位置的目标变量值（如PM2.5值和温度）进行预测。它在获取用于地方、区域和全球尺度的地理建模和决策的异质空间信息（例如土壤条件、降水率、小麦产量）方面，对地球科学的关键研究课题有重大影响。由地面原位传感器收集的原位数据以及由卫星或飞机收集的遥感数据是这项任务的两个重要数据源。原位数据相对准确，但稀疏且分布不均。遥感数据覆盖大面积空间，但粗糙，时空分辨率低且容易受到干扰。如何协同这两种数据类型的互补优势仍然是一个巨大的挑战。此外，在处理空间自相关和异质性之间的权衡时，对未知的空间预测映射进行建模是困难的。第三，在不造成大量信息损失的情况下表示空间关系也是一个关键问题。为了应对这些挑战，我们提出了一种新的异构自监督空间预测（HSSP）框架，该框架通过最小化原位观测和遥感观测之间的不一致来协同多源数据。我们提出了一种新的深度几何空间插值模型作为预测主干，该模型通过考虑距离和方向信息，根据现有观测自动对未知位置的目标变量值进行插值。我们提出的插值器被证明既是流行插值方法的一般形式，又能保留空间信息。通过一种新的误差补偿框架来增强空间预测，以捕捉由于空间异质性导致的预测不一致。我们在真实数据集上进行了大量实验，并证明了我们的模型在性能上优于最先进的模型。