Skip to content
GeoVitaIntelligence

Research

The science that powers GeoVita.

Our technology is translated from a research foundation in remote sensing, GIS, photogrammetry, GeoAI, machine learning and environmental modelling.

Research areas

A vector-surveillance evidence chain.

01

Larval-habitat detection

Radar time series, high-resolution surface models and soil data locate aquatic breeding sites.

02

Environmental suitability

Temperature, vegetation, wetness, rainfall, soil and terrain combined into suitability maps.

03

Vector abundance

Time-series analysis of remote sensing and weather linked to vector observations.

04

Disease-risk mapping

GIS and neural-network frameworks for malaria and cutaneous leishmaniasis risk.

05

Spatiotemporal forecasting

Recurrent and convolutional-recurrent deep learning under leakage-controlled validation.

06

Decision support

Reproducible pipelines, WebGIS and priority maps for field teams.

Method

From raw observation to approved output.

  1. 1

    Acquire

    Satellite, UAV, climate, terrain, vector and field data with source and licence metadata.

  2. 2

    Prepare

    Quality screening, correction, masking and harmonised grids, units and dates.

  3. 3

    Derive

    Indices, time-series composites, spatial features and labels for each question.

  4. 4

    Model

    Statistical, machine-learning and deep-learning models with versioned artefacts.

  5. 5

    Validate

    Spatial and temporal transfer, calibration, uncertainty and baseline comparison.

  6. 6

    Deliver

    Maps, dashboards, APIs and reports with human interpretation.

Validation principles

How we avoid impressive-but-wrong models.

A satellite-derived habitat or suitability map is an environmental decision-support layer. It is not direct evidence of pathogen presence, an individual diagnosis or a substitute for entomological and epidemiological surveillance.

  • 01

    Spatially separated folds so nearby samples never leak between training and testing

  • 02

    Untouched temporal holdouts to measure performance on future years

  • 03

    Comparison with simple baselines such as persistence or historical means

  • 04

    Complementary metrics, bias, calibration and uncertainty — never one headline number

  • 05

    Performance inspected by geography, year and burden stratum

  • 06

    Precise language: a habitat probability is not disease incidence

Publications

Selected peer-reviewed work.

A cross-section of the founding team's research and collaborations.

  • 2026

    Forecasting★

    Open Data GeoAI Forecasting of Malaria Endemicity across Africa: A Leakage-Controlled Comparison of Spatial and Temporal Generalization

    Youssefi, F., Valadan Zoej, M.J., Hanafi-Bojd, A.A., Khorrami, B., Ghaderpour, E., Liu, X., Li, J.

    Peer-reviewed article

    Data & code

  • 2026

    Habitats★

    A two-steps remote sensing and machine learning framework for predicting malaria-prone areas by mapping Anopheles larval habitats

    Rezvan, H., Valadan Zoej, M.J., Hassanpour, G., Youssefi, F., Hanafi-Bojd, A.A., Ghaderpour, E.

    Earth Systems and Environment, 10, 5977–5998

    DOI

  • 2026

    Risk mapping

    GIS-based neural network framework for zoonotic cutaneous leishmaniasis risk mapping in Western Iran

    Parto Dezfooli, F., Valadan Zoej, M.J., Youssefi, F., et al.

    Environmental Monitoring and Assessment, 198, 357

    DOI

  • 2026

    Risk mapping

    The influence of climatic factors and vector control on malaria incidence in southeast Iran: a 23-year longitudinal analysis

    Dehghan, A., Rahimi Foroushani, A., Rahimi, M., Nejati, J., Youssefi, F., Nikpour, F., Raeisi, A., Hanafi-Bojd, A.A.

    Parasitology

    DOI

  • 2024

    Habitats

    Identification of aquatic habitats of Anopheles mosquito using time-series analysis of Sentinel-1 data through Google Earth Engine

    Rezvan, H., Valadan Zoej, M.J., Hassanpour, G., Youssefi, F., Hanafi-Bojd, A.A.

    ISPRS Archives, XLVIII-3-W3-2024, 63–68

    DOI

  • 2024

    Risk mapping

    Predicting the environmental suitability for Anopheles stephensi under the current conditions in Ghana

    Ismail, R.B.Y., et al.

    Scientific Reports, 14, 1116

    DOI

  • 2022

    Habitats★

    Predicting the location of larval habitats of Anopheles mosquitoes using remote sensing and soil type data

    Youssefi, F., Valadan Zoej, M.J., Hanafi-Bojd, A.A., Borhani Dariane, A., Khaki, M., Safdarinezhad, A.

    International Journal of Applied Earth Observation and Geoinformation, 108, 102746

    DOI

  • 2022

    Forecasting

    Temporal monitoring and predicting of the abundance of malaria vectors using time-series analysis of remote sensing data through Google Earth Engine

    Youssefi, F., Valadan Zoej, M.J., Hanafi-Bojd, A.A., Borhani Dariane, A., Khaki, M., Safdarinezhad, A., Ghaderpour, E.

    Sensors, 22(5), 1942

    DOI

  • 2022

    Environment

    Estimation of heavy metal concentrations (Cd and Pb) in plant leaves using optimal spectral indicators and artificial neural networks

    Fakhri, A., Valadan Zoej, M.J., Safdarinezhad, A., Yavari, P.

    Environmental Science and Pollution Research, 29, 76119–76134

    DOI

Want this for your region?

We co-design pilots with local partners, data and validation.

Propose a pilotExplore the live demo