←
S.M. Labib886 posts
S.M. Labib avatar

S.M. Labib

@smlabib

Asst. Professor @UniUtrecht, Visiting scholar @Cambridge_Uni| Researcher in Spatial Data Science, GIS, Health Geography | Alum: @OfficialUoM | My views | He/Him

◷ Joined March 2013▧ 83 Photos and videos
S.M. Labib avatar
S.M. Labib@smlabib·25 Apr 2024

Health can be influenced by multiple environmental exposures & their interactions, and how we can consider them within a spatial machine learning (ML) model; check out the 📢new paper exploring these complex aspects using explainable AI tools! (1/3) doi.org/10.1016/j.scitotenv.…

Post attachment
Robin Cole avatar
⟳ S.M. Labib retweeted
Robin Cole@robmarkcole·1 Sep 2024

📢TorchGeo 0.6.0 is now released! This adds 18 new datasets, 15 new datamodules, and 27 new pre-trained models, encompassing 11 months of work by 23 contributors 🔥 The mission is for machine learning experts to work with geospatial data, and for remote sensing experts to explore machine learning solutions 👩‍💻 github.com/microsoft/torchge…

Post attachment
S.M. Labib avatar
S.M. Labib@smlabib·21 May 2024

Finally, we observed that the high CC-risk grass patches are primarily located in areas of higher socioeconomic deprivation. Indicating loss of ecosystem function for the most vulnerable population group under increasing climate change pressure (4/4)

S.M. Labib avatar
S.M. Labib@smlabib·21 May 2024

Our result showed that grass patches lose considerable evapotranspiration capacity due to water stress, that most vulnerable areas are in high-density urban zones, and that groundwater access may reduce the pressure if watered during high water stress conditions (3/4).

S.M. Labib avatar
S.M. Labib@smlabib·21 May 2024

In this study, we modeled the risk of grass layers in Greater Manchester. We applied the IPCC risk framework to locate the risk of grasses to water stress, urban fragmentation, and adaptive capacity due to groundwater access (2/4).

S.M. Labib avatar
S.M. Labib@smlabib·21 May 2024

Green infrastructure (GI)🌱 provides ecosystem services to offset the effect of climate change (CC), but what if they cannot function? How can we measure the risk GI from CC? Check out our (Jeremy Carter, @Mell_GIPlanning) new paper exploring these (1/4): t.ly/EOSN1

Post attachment
S.M. Labib avatar
S.M. Labib@smlabib·25 Apr 2024

The nonlinear relations & exposure interactions are critical to understanding the sweet & sour spots of exposures & their influence on health outcomes (3/3)

Post attachment
S.M. Labib avatar
S.M. Labib@smlabib·25 Apr 2024

This study showed using ML for health data analysis for environmental exposures (e.g., air pollution, greenspace) is not free of spatial autocorrelations & typical ML modeling structure may be sub-optimal as they might over or underestimate the influences of exposures (2/3)

Yuchen Li avatar
⟳ S.M. Labib retweeted
Yuchen Li@Yuchenn_·12 Apr 2024

Thrilled to share our latest publication in @ijgis! 🎉 Our review dives into how street view imagery and cutting-edge visual intelligence techniques are reshaping built environment auditing. Check out our full article for more: doi.org/10.1080/13658816.202…