Qingqing S.

Key Skills

Software

Other

Top Subject Matter

Environmental Science & Water Quality Monitoring

Hydrology, Reservoir and Watershed Modeling

Machine Learning for Scientific Data

Top Data Types

Image

Top Task Types

Fine-tuning

Data Collection

Polygon

Freelancer Overview

I have extensive experience working with large-scale scientific datasets, environmental monitoring data, and machine learning applications through over ten years of research in environmental science, hydrology, and geochemistry. Currently, as a postdoctoral researcher at the University of Missouri, I work with complex datasets including water quality monitoring, image-based analysis, environmental sensors, and ecological observations. My work frequently involves data cleaning, annotation, quality control, feature extraction, and integrating heterogeneous datasets for AI and statistical modeling. I have experience using Python, machine learning frameworks, and data-driven approaches to process and analyze structured and unstructured data. In addition, I have applied deep learning and image analysis techniques in interdisciplinary projects involving environmental monitoring and image-based classification. My experience includes labeling and interpreting scientific data, validating datasets, identifying patterns, maintaining data accuracy, and ensuring high-quality outputs for research and predictive modeling. My strong analytical skills, attention to detail, scientific training, and experience handling complex datasets allow me to contribute effectively to AI training data and data labeling projects.

Labeling Experience

Harmful Algal Bloom FlowCam Image Annotation and AI-Based Classification Project

ImageObject Detection

As a postdoctoral researcher at the University of Missouri, I have been involved in a harmful algal bloom (HAB) monitoring project using FlowCam image systems and AI-assisted image analysis. The project focuses on identifying and classifying phytoplankton and algae species from large-scale aquatic image datasets for environmental monitoring and early bloom detection. My responsibilities include image labeling, species annotation, quality assurance, dataset validation, and preprocessing of image data for machine learning applications. I worked with high-volume image datasets and participated in data curation and annotation workflows to improve classification accuracy. Tasks included categorizing algae morphology, identifying species characteristics, correcting labeling inconsistencies, and supporting training datasets for computer vision and deep learning models. I also used Python and machine learning tools for data processing, feature extraction, and image-based analysis. This work required strong attention to detail, consistency in annotation standards, and experience handling scientific datasets for AI model development.

2024 - Present

Education

Work History