← Back to all news
arXiv Machine Learning By Talha Ansar (University of Engineering and Technology, Lahore, Pakistan), Waqar Muhammad Ashraf (The Alan Turing Institute, London, UK), Alejandro Coca-Castro (The Alan Turing Institute, London, UK), Manvendra Janmaijaya (The Alan Turing Institute, London, UK), Ramit Debnath (University of Cambridge, Cambridge, UK), J. Scott Hosking (The Alan Turing Institute, London, UK)

Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK

Read the original on arXiv Machine Learning →

The paper presents a data‑driven framework for optimal sensor placement in aerosol monitoring across the UK. It integrates a convolutional Gaussian neural process into the DeepSensor optimisation framework, using genetic optimisation with lazy evaluation and caching to cut computational time by 60% while matching the performance of a greedy solver. The approach achieves a 22% improvement in Joint NLL for Joint‑MI‑driven genetic placement after selecting five stations, and shows that model‑based criteria align with oracle benchmarks under certain meteorological conditions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 28

Nowcasting aerosol particle size distributions from PM2.5 with physics-regularized flow matching

The paper investigates whether generative deep learning models can nowcast aerosol particle size distributions (PSDs) from routine PM2.5 measurements and meteorological data. Using data from two Finnish stations—Hyytiälä (boreal forest) and Kumpula (urban)—the authors benchmark six generative models against deterministic and climatological baselines, finding that flow matching, especially its guided variant, achieves the lowest continuous ranked probability score (CRPS). Incorporating a physics-based constraint derived from a reduced aerosol general dynamic equation further improves performance, reducing CRPS by 5.5–11.5% at the training site and improving transferability between sites.

By Zhi-Song Liu, Jenni K\"oykk\"a, Wenqing Peng, Ammar Kheder, Petri Clusius, Michael Boy
diffusionbenchmarks
More like this →
arXiv Machine Learning
Oct 9

Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model

The paper presents a six‑month dataset of indoor air‑quality measurements from low‑cost and reference sensors, collected at five locations with contextual metadata. It defines four evaluation scenarios—reference‑efficient, location‑transfer, long‑term drift, and event‑conditioned—to test spatial generalization and robustness to distribution shifts. A lightweight temporal model that compresses input windows and fuses residual temporal and feature information achieves strong calibration performance across all scenarios while keeping edge‑inference cost low.

By Jinyong Yun, Seokho Ahn, Hyungjin Kim, Sungbok Shin, Young-Duk Seo
More like this →
arXiv AI
Aug 11

AirFlow: Context Preserving and Multi-Rate State Modeling for Air Quality Forecasting

arXiv:2608. 09775v1 Announce Type: new Abstract: Accurate air quality forecasting is essential for public health and urban environmental management, but remains challenging because pollutant channels differ in periodicity and distribution drift, while their concentration trajectories contain both multi-scale dependencies and rapid changes.

By Fan Yang, Nan Chen, Yijie Dong, Yuchen Zhang, Wei Zhang
benchmarksdata-engineering
More like this →