Marston H. D. Franceschini

Remote and proximal sensing for crop monitoring · Brazil

ORCID Google Scholar ResearchGate LinkedIn GitHub

About

I work on proximal and remote sensing for monitoring crops and the stresses that affect them, especially plant diseases. I acquire, process and analyse multispectral and hyperspectral imagery from UAVs, as well as field and laboratory spectral data, to characterise plant traits and detect diseases early. My current research combines optical sensing and artificial intelligence for high-throughput plant phenotyping and digital plant pathology.

I am an agronomic engineer, with an MSc in soil and plant nutrition and a PhD in geo-information science and remote sensing from Wageningen University & Research. I develop open and reproducible workflows for sensing data in Python and R, aimed at practical use in agriculture. I work in Portuguese, English and French.

Research themes

Plant disease detection

Early detection and severity assessment of plant diseases from spectral data and UAV imagery: late blight and blackleg in potato, Ceratocystis wilt in eucalyptus.

Publications on this theme

UAV-based remote sensing

Acquisition and preprocessing of multispectral and hyperspectral UAV imagery, from radiometric correction to plant traits, including the structure of the canopy from LiDAR and photogrammetry.

Publications on this theme

Crop monitoring

Retrieval of crop and grassland traits, such as biomass and nitrogen content, from UAV and Sentinel-2 data, including how to transfer calibrated models to new conditions with few new samples.

Publications on this theme

Earlier work: soil spectroscopy, from laboratory and on-the-go measurements to imaging spectroscopy and satellite images, for soil texture, properties and salinity (publications).

Publications

2025
  • Leaf Diffuse Reflectance Spectroscopy for Early Detection of Ceratocystis Wilt in Eucalyptus Cuttings
    Santiago, M.I.L., Franceschini, M.H.D., Del Ponte, E.M., do Amaral, C.H., Alfenas, R.F.
    Forest Pathology, 55(6), e70052. doi:10.1111/efp.70052
    Disease detection
2024
  • Detection of a vascular wilt disease in potato (‘Blackleg’) based on UAV hyperspectral imagery: Can structural features from LiDAR or SfM improve plant-wise classification accuracy?
    Franceschini, M.H.D., Brede, B., Kamp, J., Bartholomeus, H., Kooistra, L.
    Computers and Electronics in Agriculture, 227, 109527. doi:10.1016/j.compag.2024.109527
    Disease detectionUAV
  • Are fungicides effective in protecting pruning wounds against Ceratocystis wilt on kiwifruit vines?
    Cassol, S.A., Santos, S.A., Franceschini, M.H.D., Alexandre, F.S., Macedo, D.M., Pal, C., Del Ponte, E.M., Alfenas, A.C., Alfenas, R.F.
    Tropical Plant Pathology, 49(3), 459-465. doi:10.1007/s40858-023-00633-1
    Disease detection
2022
  • Quantification of Grassland Biomass and Nitrogen Content through UAV Hyperspectral Imagery—Active Sample Selection for Model Transfer
    Franceschini, M.H.D., Becker, R., Wichern, F., Kooistra, L.
    Drones, 6(3), 73. doi:10.3390/drones6030073
    UAVCrop monitoring
2021
  • Sen2Grass: A Cloud-Based Solution to Generate Field-Specific Grassland Information Derived from Sentinel-2 Imagery
    Hardy, T., Kooistra, L., Franceschini, M.H.D., Richter, S., Vonk, E., van den Eertwegh, G., van Deijl, D.
    AgriEngineering, 3(1), 118-137. doi:10.3390/agriengineering3010008
    Crop monitoring
  • Crop traits retrieval and disease detection in potato: UAV optical sensing for plant monitoring
    Franceschini, M.H.D.
    PhD thesis. Wageningen University. doi:10.18174/543088
    Disease detectionUAVCrop monitoring
2020
  • Automated Processing of Sentinel-2 Products for Time-Series Analysis in Grassland Monitoring
    Hardy, T., Franceschini, M.H.D., Kooistra, L., Novani, M., Richter, S.
    Book chapter. IFIP Advances in Information and Communication Technology, 48-56. doi:10.1007/978-3-030-39815-6_5
    Crop monitoring
2019
  • Object-Based Image Analysis Applied to Low Altitude Aerial Imagery for Potato Plant Trait Retrieval and Pathogen Detection
    Siebring, J., Valente, J., Franceschini, M.H.D., Kamp, J., Kooistra, L.
    Sensors, 19(24), 5477. doi:10.3390/s19245477
    Disease detectionUAVCrop monitoring
  • UAV based soil salinity assessment of cropland
    Ivushkin, K., Bartholomeus, H., Bregt, A.K., Pulatov, A., Franceschini, M.H.D., Kramer, H., van Loo, E.N., Jaramillo Roman, V., Finkers, R.
    Geoderma, 338, 502-512. doi:10.1016/j.geoderma.2018.09.046
    UAVSoil spectroscopy
  • Feasibility of Unmanned Aerial Vehicle Optical Imagery for Early Detection and Severity Assessment of Late Blight in Potato
    Franceschini, M.H.D., Bartholomeus, H., van Apeldoorn, D.F., Suomalainen, J., Kooistra, L.
    Remote Sensing, 11(3), 224. doi:10.3390/rs11030224
    Disease detectionUAV
  • Robust soil mapping at the farm scale with vis–NIR spectroscopy
    Ramirez‐Lopez, L., Wadoux, A.M.J.‐., Franceschini, M.H.D., Terra, F.S., Marques, K.P.P., Sayão, V.M., Demattê, J.A.M.
    European Journal of Soil Science, 70(2), 378-393. doi:10.1111/ejss.12752
    Soil spectroscopy
2018
  • Improvement of Clay and Sand Quantification Based on a Novel Approach with a Focus on Multispectral Satellite Images
    Fongaro, C.T., Demattê, J.A.M., Rizzo, R., Lucas Safanelli, J., Mendes, W.d.S., Dotto, A.C., Vicente, L.E., Franceschini, M.H.D., Ustin, S.L.
    Remote Sensing, 10(10), 1555. doi:10.3390/rs10101555
    Soil spectroscopy
  • Effects of external factors on soil reflectance measured on-the-go and assessment of potential spectral correction through orthogonalisation and standardisation procedures
    Franceschini, M.H.D., Demattê, J.A.M., Kooistra, L., Bartholomeus, H., Rizzo, R., Fongaro, C.T., Molin, J.P.
    Soil and Tillage Research, 177, 19-36. doi:10.1016/j.still.2017.10.004
    Soil spectroscopy
2017
  • Assessing changes in potato canopy caused by late blight in organic production systems through UAV-based pushbroom imaging spectrometer
    Franceschini, M.H.D., Bartholomeus, H., van Apeldoorn, D., Suomalainen, J., Kooistra, L.
    Conference paper. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W6, 109-112. doi:10.5194/isprs-archives-XLII-2-W6-109-2017
    Disease detectionUAV
  • Intercomparison of Unmanned Aerial Vehicle and Ground-Based Narrow Band Spectrometers Applied to Crop Trait Monitoring in Organic Potato Production
    Franceschini, M.H.D., Bartholomeus, H., Van Apeldoorn, D., Suomalainen, J., Kooistra, L.
    Sensors, 17(6), 1428. doi:10.3390/s17061428
    UAVCrop monitoring
2015
  • Prediction of soil properties using imaging spectroscopy: Considering fractional vegetation cover to improve accuracy
    Franceschini, M.H.D., Demattê, J.A.M., da Silva Terra, F., Vicente, L.E., Bartholomeus, H., de Souza Filho, C.R.
    International Journal of Applied Earth Observation and Geoinformation, 38, 358-370. doi:10.1016/j.jag.2015.01.019
    Soil spectroscopy
  • Spectral sensing from ground to space in soil science: state of the art, applications, potential, and perspectives
    Book chapter. Land Resources Monitoring, Modeling, and Mapping with Remote Sensing (CRC Press). doi:10.1201/b19322
    Soil spectroscopy
2013
  • Abordagens semiquantitativa e quantitativa na avaliação da textura do solo por espectroscopia de reflectância bidirecional no VIS-NIR-SWIR
    Franceschini, M.H.D., Demattê, J.A.M., Sato, M.V., Vicente, L.E., Grego, C.R.
    Pesquisa Agropecuária Brasileira, 48(12), 1569-1582. doi:10.1590/S0100-204X2013001200006
    Soil spectroscopy

Software

MicaSense radiometric correction

Radiometric correction of MicaSense multispectral images, from raw values to radiance or reflectance, with the reference panel and optional DLS correction. User interface, command line and Python library.

Documentation · Code

Field design extraction

Reads field trial maps and disease rating sheets from Excel workbooks, as they are drawn in the field, and turns them into tidy tables, with data checks and figures.

Code

Ceratocystis wilt detection

Data analysis of the study on leaf diffuse reflectance spectroscopy for the early detection of Ceratocystis wilt in eucalyptus cuttings.

Code

Uncertainty-based model transfer

Analysis of the study on grassland biomass and nitrogen content from UAV hyperspectral imagery, with active sample selection for model transfer.

Code

Experience

Education

Contact

The profiles below are the best way to reach me.

ORCID Google Scholar ResearchGate LinkedIn GitHub