Dr. Sergio Marconi (He/Him)
Post-Doc at University of Florida
School of Forest, Fisheries, and Geomatics Sciences
Biography
Sergio Marconi is a Post-Doc researcher at University of Florida, interested in cross-scale patterns and ecological processes that shape forest ecosystems structure, functions and diversity. His work focuses on developing machine and statistical learning methods to leverage the ecological information held in remote sensing and field big datasets.
Download my CV.
Interests
- Computer Vision
- Forest Ecology
- Macroecology
- Remote Sensing
- Artificial Intelligence
Education
PhD in Interdisciplinary Ecology, 2020
University of Florida
MSc in Forest and Environmental Science, 2014
University of Tuscia
Skills
Forest System Modeling
Forest Ecology
Remote Sensing
Machine and Deep Learning
Python
R
Statistics
Big Data
GIS
Experience
Post-doc
University of Florida
- Cross-scale effects of ecological drivers on forest structure and function
- AI for estimating tree structural properties from NEON Remote Sensing
- Developing derived datasets of million individual trees algorithmically
PhD
University of Florida
- AI for estimating individual tree properties at scale
- AI for classification of individual trees for ~80 species
- Hierarchical modeling of leaf properties distribution across the US
- Organization of data science competition in ecology
Researcher
Euro-Mediterranean Center on Climate Change (CMCC)
- Co-development of the 3D-CMCC Forest Ecosystem Model (phenology and soil)
- Analysis of biophysical effects of Land Cover Change on climate
Funding
NSF Macrosystem Grant (NSF)
US-Italy Fulbright
Projects
*
IDTreeS
Cross-scale effects of ecological processes on ecological patterns
D3-ForScale
Data driven discovery of forest functions across scales.
Coupled Modeling of Carbon Exchange
Process based modeling for terrestrial Carbon exchange forecasting
Talks
Recorded Talks
*
Disentangling the role of ecological drivers on forest biological dimensions
Leveraging machine learning to estimate individual trees properties at scale from field and airborne imagery.
Featured Publications
Disentangling the roles of inter and intraspecific variation on leaf trait distributions across the eastern United States
Functional traits are central to how organisms perform and influence ecosystem function. Although phylogenetic constraints and environmental conditions are both known to affect trait distributions, data limitations have resulted in large scale …
A remote sensing derived data set of 100 million individual tree crowns for the National Ecological Observatory Network
Forests provide biodiversity, ecosystem, and economic services. Information on individual trees is important for understanding forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data …
Rethinking the fundamental unit of ecological remote sensing: Estimating individual level plant traits at scale
Functional ecology has increasingly focused on describing ecological communities based on their traits (measurable features of individuals that affect their fitness and performance). Analyzing trait distributions within and among forests could …
DeepForest: A Python package for RGB deep learning tree crown delineation
Remote sensing of forested landscapes can transform the speed, scale and cost of forest research. The delineation of individual trees in remote sensing images is an essential task in forest analysis. Here we introduce a new Python package, DeepForest …
A data science challenge for converting airborne remote sensing data into ecological information
Ecology has reached the point where data science competitions, in which multiple groups solve the same problem using the same data by different methods, will be productive for advancing quantitative methods for tasks such as species identification …
The role of respiration in estimation of net carbon cycle: coupling soil carbon dynamics and canopy turnover in a novel version of 3D-CMCC forest ecosystem model
Understanding the dynamics of organic carbon mineralization is fundamental in forecasting biosphere to atmosphere net carbon ecosystem exchange (NEE). With this perspective, we developed 3D-CMCC-PSM, a new version of the hybrid process based model …
Continental-scale Hyperspectral tree species classification in the National Ecological Observatory Network
Advances in remote sensing imagery and computer vision applications unlock the potential for developing algorithms to classify individual trees from remote sensing at unprecedented scales. However, most approaches to date focus on site-specific …
Recent Publications
(2022).
Data Carpentry for Biologists: A semester long Data Carpentry course using ecological and other biological examples.
Journal of Open Source Education.
(2021).
A benchmark dataset for canopy crown detection and delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network.
PLoS computational biology.
(2021).
Expanding NEON biodiversity surveys with new instrumentation and machine learning approaches.
Ecosphere.
(2021).
RandCrowns: A Quantitative Metric for Imprecisely Labeled Tree Crown Delineation.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
Contact
- sergio [dot] marconi [at] weecology [dot] org
- Gainesville, FL 32603