Welcome to Fujiang Ji's Webpage

About me

    I'm Fujiang Ji, currently a Ph.D. student at the Department of Forest and Wildlife Ecology, University of Wisconsin-Madison. My current research focuses on plant functional traits and functional diversity estimation using hyperspectral imaging spectroscopy at both leaf and canopy scales over multiple ecological functional areas; Multi-source remote sensing data fusion (spaceborne, airborne hyperspectral and multispectral data) using deep learning techniques.

    Before joining UW-Madison, I earned a Master's degree in Cartography and Geographic Information System from Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China. My master's research integrated process-based modeling, remote sensing and data assimilation to estimate crop yield, soil available nutrients, etc. Besides, I received a bachelor's degree in Remote Sensing Science and Technology from Chengdu University of Technology, Chengdu, China.

    Research_overview

Education

  1. University of Wisconsin-Madison, WI, U.S.

    2021 — Present

    • Forestry, Ph.D.

    • Department of Forest and Wildlife Ecology.

  2. Chinese Academy of Sciences, Beijing, China.

    2018 — 2021

    • Cartography and Geographic Information System, MSc.

    • Aerospace Information Research Institute.

  3. Chengdu University of Technology, Chengdu, China

    2014 — 2018

    • Remote sensing science and technology, BEng.

    • College of Earth Science

News

    1. May 20, 2025: Excited to share our new study published in Remote Sensing of Environment, led by Fujiang, which Reveals how transfer learning enhances leaf trait prediction across ecosystems (Link to article).
    2. Apr 11, 2025: Fujiang has been awarded the department’s Joon Lee Award in recognition of his outstanding academic performance.
    3. Dec 11, 2024: Presented our work about tracking seasonal variations of plant traits using multi-source hyperspectral data across NEON sites on AGU 2024! (Link)
    4. Nov 22, 2024: Led by Haoran, our new study published in Remote Sensing of Environment, which reveals near-infrared reflectance of vegetation (NIRvP) in the “hotspot” direction offers a stronger correlation with GPP than nadir observations (Link to article).
    5. Oct 19, 2024: Our paper published in Earth's Future on projecting large fires in the western US using a hybrid physical-ML model (AttentionFire v2.0). Led by Fa (Link to article).
    6. Sep 11, 2024: Participated in the Three Minute Thesis competition at the University of Wisconsin-Madison, titled "Eyes in the sky: Decoding plant functional traits with imaging spectroscopy"
    7. May 06, 2024: Fujiang led a publication in New Phytologist on the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset (Link to article).
    8. Apr 30, 2024: Fujiang has been awarded the department’s annual Thomas O’Brien Award.
    9. Feb 25, 2024: Presented our work on Bryson Scholarship Poster Session at UW-Madison.
    10. Sep 14, 2023: Our paper “Structural complexity biases vegetation greenness measures” has been published in Nature Ecology & Evolution (Link to article).
    11. Dec 15, 2022: Presented our work on AGU 2022 in Chicago!
    12. Sep 01, 2021: Excited to join the Global Change Research Laboratory in the Department of Forest & Wildlife Ecology at the University of Wisconsin–Madison, led by Prof. Min Chen.

Research Interests

  • plant traits

    Leaf functional traits

    Predicting leaf traits by integrating hyperspectral RS and various modeling methods at canopy and leaf scales.

  • remote sensing

    hyperspectral RS

    Leaf spectroscopy: ASD, SVC, PSR, etc. Imaging spectroscopy: PRISMA, SBG, EnMap, DESIS, AVIRIS, etc.

  • RTM

    Radiative transfer modeling

    PROSPECT, PROSAIL, Leaf-Canopy SIP models,etc.

  • Functional diversity

    Forest Functional Diversity

    Forest functional diversity (richness, divergence and evenness).

  • CLM

    Land surface model

    Learn land surface processes and the interactions between the land surface and the atmosphere.

  • ML

    Machine Learning

    Utilize advanced ML algorithms to estimate leaf traits, predict wildfire, etc.

  • Crop yield

    Crop yield estimation

    Regional scales crop yield estimation based on crop growth models and data assimilation methods.

  • WOFOST

    Crop growth modeling

    integrate various factors (weather, soil, etc) to predict crop growth, yield, and response to environmental factors.

Projects and Research Experiences

    1. Graduate Research Assistant, University of Wisconsin-Madison, September, 2021 – December, 2025 (Expected).
      1. Advance spaceborne mapping of plant functional traits with high-resolution and hyperspectral data over sparse vegetation canopies (80NSSC24K0054), March, 2024 – December, 2025 (Expected).

        2. Proposed a novel framework for data fusion and enable large-scale, repeatable plant functional trait mapping in sparsely vegetated areas through the unique combination of small commercial satellite sensors (PlanetScope) and hyperspectral DESIS or EMIT data.

      2. Monitoring and understanding seasonal variations of forest functional traits and diversity by integrating observations from multi-source RS data, September, 2021– December, 2024.

        3. Using satellite hyperspectral data (PRISMA), NEON AOP data, in-situ leaf spectra and traits as well as different modeling methods (empirical, physical, hybrid) to investigate how does functional traits vary over the growing season and across different forest ecosystems (different NEON sites).

    2. Graduate Research Assistant, Aerospace Information Research Institute, Chinese Academy of Sciences, September, 2018 – June, 2021.
      1. China High-resolution EO System – Quantitative Retrieval Technology of Vegetation Parameters from GF-6 WFV Satellite Image (30-Y20A03-9003-17/18-05), 2018-2019.

        2. Using the WFV wide camera of the GF-6 satellite to estimate the yield of crops in the Xinjiang experimental area. I mainly completed the combination of the crop model and data assimilation algorithm based on the IDL language.

      2. The STS (Science and Technology Service Network Initiative) Program of Chinese Academy of Sciences (KFJ-EW-STS-069), 2019-2020.

        3. Conducted field campaigns and remote sensing monitoring at the field scale, including crop physiological/biochemical parameters retrieval, crop conditions, biomass, soil nutrient status, yield monitoring, etc. Also arranged monthly project meetings and draft monthly progress reports.

      3. “Big Earth Data” Science Engineering Project of Chinese Academy of Sciences (CASEarth) – Big Earth Data Supports the U.N. Sustainable Development Goals (SDGs), 2020.

        4. Produced the 2000-2019 farmland productivity dataset in Northeast Eurasia by using the crop growth model through the JavaScript API interface of the Google Earth Engine platform; Wrote the SDGs 2.4 documents in both Chinese and English.

      4. Precision Insurance of Wheat Based on Spatial Big Data, 2018-2019.

        5. Assimilating time-series remotely sensed data into crop growth to realize yield estimation, and crop disaster level assessment, and established a wheat insurance technical system.

    3. Undergrad Research Assistant, Chengdu University of Technology, September – December, 2016.
      1. Research on technologies used to demarcate red-line areas of ecology in major districts and counties of Sichuan Province, China, initiated by a professor in the department, 2016.
    4. Project Leader, Chengdu University of Technology, 2017 – 2018.
      1. National College Students' innovation and entrepreneurship training program (Grant No. 201710616032), 2017-2018.

        2. Inversion and Detection of Parameter of the Growing Status of Rice based on Hyperspectral Data.

Service

    1. Reviewer for scientific Journals: Agricultural and Forest Meteorology; Earth System Science Data; Remote Sensing; IEEE Transactions on Geoscience and Remote Sensing; Science of the Total Environment, Frontiers of Earth Science.

Daniel lewis

Organizations

Skills

  • 1. Programming: Python, R, ENVI/IDL, MATLAB, JavaScript
    90%
  • 2. Models: World Food Studies (WOFOST), AquaCrop, PROSPECT, PROSAIL, Leaf-SIP.
    80%
  • 3. Computing: High throughput computing (HTC), High Performance computing (HPC).
    90%
  • 4. GIS and Remote sensing software: GEE, ArcGIS, QGIS, ENVI, SNAP, ERDAS.
    90%
  • 5. Instruments: LAI 2200, SPAD 502, TDR 300, etc.
    70%
  • 6. Remote sensing data processing, algorithm design and system development.
    90%