Recent developments in data mining and machine learning approaches have brought lots of excitement in providing solutions for challenging tasks (e.g., computer vision). However, many approaches have limited interpretability, so their success and failure modes are difficult to understand and their scientific robustness is difficult to evaluate. Thus, there is an urgent need for better understanding of the scientific reasoning behind data mining and machine learning approaches. This requires taking a transdisciplinary view of data science and recognizing its foundations in mathematics, statistics, and computer science. Focusing on the geospatial domain, we apply this crucial transdisciplinary perspective to five common geospatial techniques (hotspot detection, colocation detection, prediction, outlier detection and teleconnection detection). We also describe challenges and opportunities for future advancement.

Given a spatial graph, an origin and a destination, and on-board diagnostics (OBD) data, the energy-efficient path selection problem aims to find the path with the least expected energy consumption (EEC). Two main objectives of smart cities are sustainability and prosperity, both of which benefit from reducing the energy consumption of transportation. The challenges of the problem include the dependence of EEC on the physical parameters of vehicles, the autocorrelation of the EEC on segments of paths, the high computational cost of EEC estimation, and potential negative EEC. However, the current cost estimation models for the path selection problem do not consider vehicles’ physical parameters. Moreover, the current path selection algorithms follow the “path + edge” pattern when exploring candidate paths, resulting in redundant computation. Our preliminary work introduced a physics-guided energy consumption model and proposed a maximal-frequented-path-graph shortest-path algorithm using the model. In this work, we propose an informed algorithm using an admissible heuristic and propose an algorithm to handle negative EEC. We analyze the proposed algorithms theoretically and evaluate the proposed algorithms via experiments with real-world and synthetic data. We also conduct two case studies using real-world data and a road test to validate the proposed method.

The on-demand economy has attracted significant attention in recent years, with a rapid growth in on-demand services ranging from ride-hailing to package delivery and grocery pickup. However, real-world spatio-temporal data that can be used for evaluating research on on-demand brokers design and supply-demand regulation are either not publicly available or are very limited in their spatial coverage. Research efforts in generating synthetic spatio-temporal datasets such as traffic generators have only focused on one side of the business model, particularly the demand side, and thus are not convenient for studying market variations such as the problem of supply-demand imbalance. In addition, many of these generators do not accurately reflect real-world data characteristics. In this paper, we propose a supply and demand aware framework for generating synthetic datasets for the purpose of designing on-demand spatial service brokers, while also capturing real-world data characteristics by leveraging multiple publicly available data sources. We also present an evaluation of the quality and performance of our proposed framework.