Skip to main content

This job has expired

Remote Sensing of Forest Carbon

Employer
Jet Propulsion Laboratory, CALTECH
Location
Nashville, Tennessee, US
Salary
Competitive
Closing date
Dec 4, 2022

View more

Sector
Academic / Research
Field
Conservation science
Discipline
Remote Sensing
Salary Type
Salary
Employment Type
Full time
We invite applications for a postdoctoral position with joint appointment at the Earth Science and Radar Science and Engineering section of the NASA/Jet Propulsion Laboratory (JPL) for a period of two year with possible extension to the third year based on performance and funding.
Description of Position
Researchers at the Carbon Cycle and Ecosystem group at JPL, and international partners have recently designed a global Carbon Monitoring System (CMS) based on the power of big data from space technology and artificial intelligence (AI) for climate smart forest restoration and carbon management. CMS is focused on providing precise science-based geospatial data products on carbon stocks and annual emissions and removals at the national and jurisdictional levels to empower decision makers for climate mitigation policies. In its initial phase, our team will integrate a series of optical and microwave satellite (including upcoming NISAR and BIOMASS) imagery with airborne and satellite (GEDI, ICESAT-2) lidar measurements of forest structure and conventional ground-based forest inventory data to map and monitor changes of forest structure and biomass globally and attribute the changes to land use activities and environmental effects.
The selected candidates will work with a team of scientists to conduct original research by using machine learning algorithms and process-based models to develop regional and global products and improve our understanding of drivers of carbon stock changes across a variety of ecosystems. The selected candidates may work on two distinct tasks: 1. to map forest disturbance (land use, logging, and tree mortality), fire fuel loads, and biomass carbon change across temperate forests (e.g. western US), and 2. to quantify biomass loss and gain from land use activities (deforestation, degradation), and forest regeneration (e.g. secondary forests) in humid tropical ecosystems (e.g. Amazon and Congo Basins). These tasks will help improve the quantification of global carbon cycle as a result of human and climate-induced changes and better understand the short-term and long-term responses of ecosystems to climate change. The candidates are required to lead one task, perform the analysis, document all algorithms and codes developed for data processing, analysis, science product generation, and lead peer-reviewed publications.

Responsibilities

* Machine Learning Algorithms: ML models to predict geospatial variations of forest structure and carbon using a variety of remote sensing data
* Mapping forest disturbance and recovery: Development of ML models to map forest disturbance (deforestation, degradation, fire) and recovery (regeneration, afforestation) using very high and conventional satellite data (Landsat, Sentinel, Planet, etc.).
* Mapping forest vulnerability: Modeling forest vulnerability to fire disturbance and climate such as mapping f ire fuel load, biomass carbon stock changes, and resilience analysis across boreal, temperate, and tropical forests.
* Calculation of emissions and removals: Design and implementation of analytic approaches using carbon standards to quantify and map emissions and removals from forest cover change.
* Geospatial Analysis: Design accurate and scalable geospatial prediction algorithms for forest structure and biomass, validation, and spatial analysis.
* Software & Publication: Delivery of algorithm codes to be integrated in STV information system, and peer-reviewed publications

Qualifications

* Completed PhD in one of the following areas: r remote sensing, computer science, environmental science and engineering, mathematics/statistics with relevant experience in forest ecology and geography.
* Strong expertise in remote sensing of vegetation
* Deep understanding of predictive modeling, machine-learning, clustering and statistical techniques, and algorithms
* Fluency in a programming language (Python, R, Mathlab, SQL)
* Familiarity with geospatial Big Data analysis and frameworks

Get job alerts

Create a job alert and receive personalized job recommendations straight to your inbox.

Create alert