1. Data Acquisition and Preparation
- Select collect compile and preprocess highquality timeseries satellite imagery from reliable sources using desktop or cloudbased remote sensing engines.
- Support the development of rulesets/interpretation keys and image interpretation procedures for classifying land use/cover types in Indonesia using satellite imagery.
2. Data Quality Assurance and Analysis
- Assist in performing replicable accuracy assessments and refining land use/cover data.
- Solicit and incorporate feedback from internal and external colleagues to improve land use/cover classification accuracy.
- Assist in conducting land use/cover change analysis and other related LULC analytical tasks as required.
- Contribute to the development of case studies on the application of land use/cover maps.
3. Field Survey Planning data management and documentation
- Assist in planning field surveys and organising the collected data for model training validation and accuracy assessment.
- Contribute to documenting all technical procedures for image classification including code annotation within versioncontrolled notebooks.
- Assist in organising spatial datasets into a database system.
A bachelor s degree in a relevant Science, Technology, Engineering, or Mathematics (STEM) field, including but not limited to Geomatics Engineering, Computer Engineering, Earth Sciences. A thesis or final project utilising desktop or cloud-based remote sensing platforms is a plus. Course completions related to cloud-based remote sensing platforms (e.g., Google Earth Engine) are highly valued. Two years of experience supporting remote sensing projects using cloud-based platforms is preferred. However, recent graduates with experience using cloud-based remote sensing platforms during their BSc are encouraged to apply. Proficient in written and spoken English is essential. A strong understanding of remote sensing principles and their practical application is required, encompassing knowledge of various sensors, pre-processing methods, data fusion techniques, hierarchical classification, Object-Based Image Analysis (OBIA), and accuracy assessment methodologies. Hands-on expertise assisting with projects using Google Earth Engine (GEE) or similar platforms. Specific examples of contributions to land cover mapping, land-use change monitoring, or other relevant applications are highly beneficial. Demonstrated ability to effectively manage and process remote sensing datasets within desktop environments (e.g., eCognition, ENVI, ERDAS Imagine) and cloud platforms (e.g., Google Earth Engine, Microsoft Planetary Computer), including a strong understanding of data structures, formats, and pre-processing techniques. Experience in programming and scripting languages commonly used within Google Earth Engine, such as JavaScript and Python, is preferred. Proficiency in using version control systems (e.g., Git) is highly desirable. Evidence of past contributions to shared repositories like GitHub or GitLab would be a significant asset.