Search

Large language models (LLMs) have demonstrated remarkable capabilities in document processing, data analysis, and code generation. However, the generation of spatial information in a structured and unified format remains a challenge, limiting their integration into production environments. In this paper, we introduce a benchmark for generating structured and formatted spatial outputs from LLMs with a focus on enhancing spatial information generation. We present a multi-step workflow designed to improve the accuracy and efficiency of spatial data generation. The steps include generating spatial data (e.g., GeoJSON) and implementing a novel method for indexing R-tree structures. In addition, we explore and compare a series of methods commonly used by developers and researchers to enable LLMs to produce structured outputs, including fine-tuning, prompt engineering, and retrieval-augmented generation (RAG). We propose new metrics and datasets along with a new method for evaluating the quality and consistency of these outputs. Our findings offer valuable insights into the strengths and limitations of each approach, guiding practitioners in selecting the most suitable method for their specific use cases. This work advances the field of LLM-based structured spatial data output generation and supports the seamless integration of LLMs into real-world applications. [ABSTRACT FROM AUTHOR]

Mining spatiotemporal mobility patterns is crucial for optimizing urban planning, enhancing transportation systems, and improving public safety by providing useful insights into human movement and behavior over space and time. As an unsupervised learning technique, time series clustering has gained considerable attention due to its efficiency. However, the existing literature has often overlooked the inherent characteristics of mobility data, including high-dimensionality, noise, outliers, and time distortions. This oversight can lead to potentially large computational costs and inaccurate patterns. To address these challenges, this paper proposes a novel neural network-based method integrating temporal autoencoder and dynamic time warping-based K-means clustering algorithm to mutually promote each other for mining spatiotemporal mobility patterns. Comparative results showed that our proposed method outperformed several time series clustering techniques in accurately identifying mobility patterns on both synthetic and real-world data, which provides a reliable foundation for data-driven decision-making. Furthermore, we applied the method to monthly county-level mobility data during the COVID-19 pandemic in the U.S., revealing significant differences in mobility changes between rural and urban areas, as well as the impact of public response and health considerations on mobility patterns. [ABSTRACT FROM AUTHOR]

Evacuation planning and emergency routing systems are crucial in saving lives during disasters. Traditional emergency routing systems, despite their best efforts, often struggle to accurately capture the dynamic nature of flood conditions, road closures, and other real-time changes inherent in urban disaster logistics. This paper introduces the ReinforceRouting model, a novel approach to optimizing evacuation routes using reinforcement learning (RL). The model incorporates a unique RL environment that considers multiple criteria, such as traffic conditions, hazardous situations, and the availability of safe routes. The RL agent in this model learns optimal actions through interaction with the environment, receiving feedback in the form of rewards or penalties. The ReinforceRouting model excels in executing prompt and accurate route planning on large road networks, outperforming traditional RL algorithms and shortest-path-based algorithms. A higher safety score and episode reward of the model are demonstrated when compared to these classical methods. This innovative approach to disaster evacuation planning offers a promising avenue for enhancing the efficiency, safety, and reliability of emergency responses in dynamic urban environments. [ABSTRACT FROM AUTHOR]

Layer-by-layer(LbL) deposition using primarily inorganic silicananoparticles is employed for surface modification of polymeric micro-and ultrafiltration (MF/UF) membranes to produce novel thin film composite(TFC) membranes intended for nanofiltration (NF) and reverse osmosis(RO) applications. A wide variety of porous substrate membranes withdifferent surface characteristics are successfully employed. Thisreport gives detailed results for polycarbonate track etched (PCTE),polyethersulfone (PES), and sulfonated PES (SPEES) MF/UF substrates.Both spherical (cationic/anionic) and eccentric elongated (anionic)silica nanoparticles are deposited using conditions similar to thosein prior works for solid substrates (e.g., Lee et al.1). Appropriate selection of the pH for anionic and cationicparticle deposition enables construction of nanoparticle-only layers100–1200 nm in thickness atop the original porous membranesubstrates. The surface layer thickness appears to vary linearly withthe number of bilayers deposited, i.e., with the number of anionic/cationicdeposition cycles. The deposition process is optimized to eliminatedrying-induced cracking and improve mechanical durability via thicknesscontrol and postdeposition hydrothermal treatment. “Dead-end”permeation tests using dextran standards reveal the hydraulic characteristicsand separations capability for the PCTE-based TFC membranes. The resultsshow that nanoparticle-based LbL surface modification of MF and UFrated media can produce TFC membranes with NF capabilities. [ABSTRACT FROM AUTHOR]

We report a highly sensitive and selective CNT-switch liquid biopsy platform that detects and quantifies protein biomarker expressions from circulating tumor cells in blood for early detection of metastatic breast cancer and its relapse. This platform first isolates and enriches more than 99% of tumor cells with an off-chip micro-size membrane filtration technique and then conducts on-chip detection of the membrane and internal protein biomarkers of the tumor cells with high sensitivity and selectivity. High sensitivity is achieved with complete association of the antibody-antigen-antibody (Ab-Ag-Ab) complex by precisely and rapidly assembling carbon nanotubes (CNTs) across two parallel electrodes via sequential DC electrophoresis and dielectrophoresis (DEP) deposition. Each bridged CNT acts as a switch that connects the electrodes and closes the circuit to generate an electrical signal. The high selectivity is achieved with a critical hydrodynamic shear rate that irreversibly removes non-target linkers of the aligned CNTs. At present, we are able to detect the protein biomarkers from 5 spiked breast cancer tumor cells of different types within 7.5 ml of human blood samples. This demonstrates the potential of this platform as an inexpensive and noninvasive alternative to MRI scans and tissue biopsies currently used to detect early metastatic breast cancer and its relapse., (© 2022. The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature.)