Empowering cities to embrace sustainability and take ESG decisions

ServiceTechnology

Con le nostre tecnologie cambiamo il futuro del pianeta. Identifichiamo i KPI per la sostenibilità ambientale, prendiamo decisioni ESG e analizziamo ogni dato per monitorare i progressi raggiunti.

High Spatial Resolution Land Surface Temperature map (LST 10m)

The layer is obtained by applying Latitudo 40 proprietary machine learning algorithms to Copernicus Sentinel 2 images in order to obtain a land surface temperature map for use in studying the Urban Heat Islands phenomenon. 

The map has a ground spatial resolution of 10m and is provided at a frequency of no less than one survey per week (in the absence of clouds).

Surface Urban Heat Island (SUHI)

These maps show the occurrence of the Surface Urban Heat Island (SUHI) effect on the city’s territory. 

This layer describes the average LST difference observed over a specific period (at least monthly), between each map location (10m pixel resolution) and a reference temperature value, in order to display and assess the intensity of the SUHI. It is important to highlight that UHI usually refers to the difference of air temperature between rural areas and urban areas during the night when the latter is minimum. 

 

Surface Urban Heat Island (SUHI)

These maps show the occurrence of the Surface Urban Heat Island (SUHI) effect on the city’s territory. 

This layer describes the average LST difference observed over a specific period (at least monthly), between each map location (10m pixel resolution) and a reference temperature value, in order to display and assess the intensity of the SUHI. It is important to highlight that UHI usually refers to the difference of air temperature between rural areas and urban areas during the night when the latter is minimum. 

Carbon Sequestration

The layer shows the ability of the city’s green infrastructure to absorb CO2. The layer is calculated from a very highresolution land cover map to which the estimated surface biomass,

subsurface biomass, soil characteristics and estimated dead organic matter are added in the application of the specific proprietary machine learning model.

Super Resolution

Latitudo 40 has implemented its own version of an algorithm based on a Generative Adversarial Network capable of creating products with a spatial resolution of 1m from Sentinel 2 images for the R, G, B and NIR bands.

The algorithm has been trained over time using very high spatial resolution (submetric) datasets acquired from heterogeneous sensors including, to name a few, those from the Worldview 2 and 3 satellites, Planet Labs SkySat and Airbus Pleiades.

Super Resolution

Latitudo 40 has implemented its own version of an algorithm based on a Generative Adversarial Network capable of creating products with a spatial resolution of 1m from Sentinel 2 images for the R, G, B and NIR bands.

The algorithm has been trained over time using very high spatial resolution (submetric) datasets acquired from heterogeneous sensors including, to name a few, those from the Worldview 2 and 3 satellites, Planet Labs SkySat and Airbus Pleiades.

Albedo

Surface albedo in rural and urban environments is one of the most influential parameters in assessing the effects of solar radiation on the earth’s surface. The study of UHI and, above all, of the effects of any mitigation actions taken cannot disregard an assessment of albedo.

Healt Trend

Latitudo 40 implemented a regression model based on a variation of a convolutional network used in a multitude of application scenarios (U-Net) in order to generate an information layer for the identification and classification of green infrastructures in urban environments. In this way is possible to obtain data which delineates with high precision the city areas with the presence of green (including tree-lined avenues) and which, by virtue of the intensity trends of the vegetation indices and the identification of the tree canopies (tree cover density), allows to carry out further analyses on the microclimatic performance of the green area.

Healt Trend

Latitudo 40 implemented a regression model based on a variation of a convolutional network used in a multitude of application scenarios (U-Net) in order to generate an information layer for the identification and classification of green infrastructures in urban environments. In this way is possible to obtain data which delineates with high precision the city areas with the presence of green (including tree-lined avenues) and which, by virtue of the intensity trends of the vegetation indices and the identification of the tree canopies (tree cover density), allows to carry out further analyses on the microclimatic performance of the green area.

Now it is time to take sustainable decisions supported by data.

Partner

Investors

Leadership

News

Blog post South Summit 2023 Madrid

Blog post South Summit 2023 Madrid

We had the opportunity to participate at the South Summit 2023 in Madrid. As finalists in the Mobility and Intelligent Cities category, we had the opportunity to showcase our innovative solutions and connect with industry leaders, investors, and fellow entrepreneurs...

Latitudo 40 at the ChangeNOW 2023 in Paris

Latitudo 40 at the ChangeNOW 2023 in Paris

Last week Latitudo 40 had the incredible opportunity to attend ChangeNOW 2023 in Paris, a three-day summit that brings together the greatests ideas and minds fighting for sustainability and against climate change. During the event, hosted in the Grand Palais Éphémère,...