Lv
L.W. van Blokland
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
3 records found
1
Accurate estimates for air temperatures in urban environments can help with timely and precise action against the urban heat island (UHI) effect. Uncertainty-aware spatio-temporal transformers are an ideal candidate model for producing such predictions. This study details the implementation and testing of a transformer model that combines remotely sensed land surface temperature (LST) data with in-situ sensor readings to predict air temperature values for the entirety of the Netherlands. The three best models out of the 21 trained attained an averaged test-set error of 1.365° Celsius MAE. Model inference has produced Geotiffs of air temperature and uncertainty predictions for all of the Netherlands, at a 70m by 70m pixel resolution. NASA's ECOSTRESS dataset supplied LST imagery and assorted ancillary bands, ESA's Copernicus provided NDVI and Landcover data, and sensor readings were acquired from the royal Dutch weather service (KNMI). Overall this study details the design for a spatio-temporal transformer model that produces uncertainty-aware air temperature estimations.
...
Accurate estimates for air temperatures in urban environments can help with timely and precise action against the urban heat island (UHI) effect. Uncertainty-aware spatio-temporal transformers are an ideal candidate model for producing such predictions. This study details the implementation and testing of a transformer model that combines remotely sensed land surface temperature (LST) data with in-situ sensor readings to predict air temperature values for the entirety of the Netherlands. The three best models out of the 21 trained attained an averaged test-set error of 1.365° Celsius MAE. Model inference has produced Geotiffs of air temperature and uncertainty predictions for all of the Netherlands, at a 70m by 70m pixel resolution. NASA's ECOSTRESS dataset supplied LST imagery and assorted ancillary bands, ESA's Copernicus provided NDVI and Landcover data, and sensor readings were acquired from the royal Dutch weather service (KNMI). Overall this study details the design for a spatio-temporal transformer model that produces uncertainty-aware air temperature estimations.
Student report
(2025)
-
Alexandre Bry, Daan Schlosser, Lars van Blokland, Mingjie Teo, Phuong Anh Ho, Bastiaan van Loenen, Gina Stavropoulou
A campus map serves as the gateway to information about infrastructure, facilities and services a university provides. We critique existing campus maps of TU Delft from an inclusive perspective, and propose a new 3d inclusive campus map targeted at staff and students. The map integrates both 2D and 3D spatial representations, consolidates outdoor and indoor information, and offers interactive map functionalities prioritising the needs of the underrepresented communities of the university. In fulfilment of the GEOIT1501 Synthesis Project course and our client the Diversity and Inclusion Office, our map serves as the foundation upon which future projects may build upon to continually provide a comfortable and socially safe campus grounds for all staff and students.
...
A campus map serves as the gateway to information about infrastructure, facilities and services a university provides. We critique existing campus maps of TU Delft from an inclusive perspective, and propose a new 3d inclusive campus map targeted at staff and students. The map integrates both 2D and 3D spatial representations, consolidates outdoor and indoor information, and offers interactive map functionalities prioritising the needs of the underrepresented communities of the university. In fulfilment of the GEOIT1501 Synthesis Project course and our client the Diversity and Inclusion Office, our map serves as the foundation upon which future projects may build upon to continually provide a comfortable and socially safe campus grounds for all staff and students.
Algorithms that recommend items to users are known as recommender systems and have become an important part of online ecosystems. These systems calculate the similarity between given users or items based on the ratings they have received. Such similarities can be modeled as a graph where users or items (nodes) have connections (edges) to other users or items if the ratings they possess are alike. Using a graphical representation allows for the use of graph regularisers. These techniques predict ratings for a given user or item by using the ratings of users or items that are connected to the target in the graph. For the Total Variation Regulariser, much is still unclear concerning its performance when applied to Item KNN Collaborative Filtering. This report will show why Item Total Variation was unable to out-perform more traditional recommender systems in the conducted experiments. The findings indicate how this poor performance could in part be attributed to the choice in dataset. Additional results also convey that Total Variation may be predisposed to performing worse for a certain type of metric.
...
Algorithms that recommend items to users are known as recommender systems and have become an important part of online ecosystems. These systems calculate the similarity between given users or items based on the ratings they have received. Such similarities can be modeled as a graph where users or items (nodes) have connections (edges) to other users or items if the ratings they possess are alike. Using a graphical representation allows for the use of graph regularisers. These techniques predict ratings for a given user or item by using the ratings of users or items that are connected to the target in the graph. For the Total Variation Regulariser, much is still unclear concerning its performance when applied to Item KNN Collaborative Filtering. This report will show why Item Total Variation was unable to out-perform more traditional recommender systems in the conducted experiments. The findings indicate how this poor performance could in part be attributed to the choice in dataset. Additional results also convey that Total Variation may be predisposed to performing worse for a certain type of metric.