Annalisa Sheehan

Dr. Annalisa Sheehan

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2024 in Environment International
Verified
Journal Article
Open access
XLXiansheng Liu
Xiansheng Liu
RLRosa Lara
Rosa Lara
MDMarvin Dufresne
Marvin Dufresne
LWLijie Wu
Lijie Wu
Xun ZhangXun Zhang
Xun Zhang
XQXavier Querol
Xavier Querol
This study addressed the scarcity of NH3 measurements in urban Europe and the diverse monitoring protocols, hindering direct data comparison. Sixty-nine datasets from Finland, France, Italy, Spain, and the UK across various site types, including industrial (IND, 8), traffic (TR, 12), urban (UB, 22), suburban (SUB, 12), and regional background (RB, 15), are analyzed to this study. Among these, 26 sites provided 5, or more, years of data for time series analysis. Despite varied protocols, necessitating future harmonization, the average NH3 concentration across sites reached 8.0 ± 8.9 μg/m3. Excluding farming/agricultural hotspots (FAHs), IND and TR sites had the highest concentrations (4.7 ± 3.2 and 4.5 ± 1.0 μg/m3), followed by UB, SUB, and RB sites (3.3 ± 1.5, 2.7 ± 1.3, and 1.0 ± 0.3 μg/m3, respectively) indicating that industrial, traffic, and other urban sources were primary contributors to NH3 outside FAH regions. When referring exclusively to the FAHs, concentrations ranged from 10.0 ± 2.3 to 15.6 ± 17.2 μg/m3, with the highest concentrations being reached in RB sites close to the farming and agricultural sources, and that, on average for FAHs there is a decreasing NH3 concentration gradient towards the city. Time trends showed that over half of the sites (18/26) observed statistically significant trends. Approximately 50 % of UB and TR sites showed a decreasing trend, while 30 % an increasing one. Meta-analysis revealed a small insignificant decreasing trend for non-FAH RB sites. In FAHs, there was a significant upward trend at a rate of 3.51[0.45,6.57]%/yr. Seasonal patterns of NH3 concentrations varied, with urban areas experiencing fluctuations influenced by surrounding emissions, particularly in FAHs. Diel variation showed differing patterns at urban monitoring sites, all with higher daytime concentrations, but with variations in peak times depending on major emission sources and meteorological patterns. These results offer valuable insights into the spatio-temporal patterns of gas-phase NH3 concentrations in urban Europe, contributing to future efforts in benchmarking NH3 pollution control in urban areas.

13 December 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ASAnnalisa Sheehan
Annalisa Sheehan
ABAndrew Beddows
Andrew Beddows
DGDavid Green
David Green
SBSean Beevers
Sean Beevers
Accurate traffic data is crucial for a range of different applications such as quantifying vehicle emissions, and transportation planning and management. However, the availability of traffic data is geographically fragmented and is rarely held in an accessible form. Therefore, there is an urgent need for a common approach to developing large urban traffic data sets. Utilising satellite data to estimate traffic data offers a cost-effective and standardized alternative to ground-based traffic monitoring. This study used high-resolution satellite imagery (WorldView-2 and 3) and Deep Learning (DL) to identify vehicles, road by road, in Barcelona (2017–2019). The You Only Look Once (YOLOv3) object detection model was trained and model accuracy was investigated via parameters such as training data set specific anchor boxes, network resolution, image colour band composition and input image size. The best performing vehicle detection model configuration had a precision (proportion of positive detections that were correct) of 0.69 and a recall (proportion of objects in the image correctly identified) of 0.79. We demonstrated that high-resolution satellite imagery and object detection models can be utilised to identify vehicles at a city scale. However, the approach highlights challenges relating to identifying vehicles on narrow roads, in shadow, under vegetation, and obstructed by buildings. This is the first time that DL has been used to identify vehicles at a city scale and demonstrates the possibility of applying these methods to cities globally where data are often unavailable.

25 February 2025 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
ASAnnalisa Sheehan
Annalisa Sheehan
ABAndrew Beddows
Andrew Beddows
JGJohn Gulliver
John Gulliver
DGDavid Green
David Green
SBSean Beevers
Sean Beevers

6 April 2026 in Environment International
Verified
Journal Article
Open access
ASAnnalisa Sheehan
Annalisa Sheehan
CJCalvin Jephcote
Calvin Jephcote
JGJohn Gulliver
John Gulliver
A major shortcoming of air pollution and road traffic noise models is a lack of traffic data, especially for local roads. We aimed to increase the coverage and accuracy of data on annual average daily traffic (AADT) flows on all road types to support the development of emission inventories. We developed statistical machine learning approaches (Random Forest - RF; extreme gradient boosting - XGB; generalised linear mixed model - GLMM) to model AADT, using open-data on measured traffic flows from 4744 sites, covering 12 areas in 7 European Countries. Traffic flow predictor variables (N = 51) described the types of roads, road network connectivity, population, drive-time, land use and topography. A 1000-fold cross-validation procedure was used in model training and testing, where a randomly stratified (by road type and area) selection of 80% of traffic counting sites were used to train models, with the remaining 20% of sites reserved for model testing. The predictions for all reserved sites from the 1000 iterations were pooled to provide an 'ensemble' prediction for each site. For performance evaluation, we compared 'single' models developed using the whole dataset with models 'combined' from road-type sub-models (highways, local, residential). RF and XGB performed similarly overall (R2: 0.85-0.86) and outperformed GLMM (R2: 0.69-0.73). The 'combined' method slightly outperformed 'single' models overall, with notably better performance for residential roads by using sub-models. For transferability to other areas, we recommend testing the need for local calibration of the models (i.e., regression) using measurements of AADT covering different road types.