Sim Sanghera
A Data Scientist in Wastershed Technology
What Do They Do?
“I’m a generalist technologist who builds data pipelines and ML tools that turn complex data (like watershed and climate data) into real, usable insight.”
Sim works across different parts of the technology stack, from building the data pipelines that make information usable to developing machine-learning tools that identify patterns and anomalies in climate and watershed data. These tools can help people explore long-term climate scenarios and extreme events, or make complex information easier for watershed managers to visualize, interpret, and use.
A large part of the work happens behind the scenes. Before a model can generate insights or a dashboard can make information accessible, messy data needs to be found, organized, cleaned, and made usable. For Sim, this less glamorous side of data science is critical: machine-learning and AI models depend on good-quality data. Done well, that work helps turn complex environmental information into evidence that can support better decisions about watersheds.
Why Does It Matter?
For Sim, the urgency of this work is difficult to ignore. Climate change is already affecting watersheds through more frequent droughts, floods, extreme events, and water-quality challenges. But she remains optimistic about our ability to respond: “It’s not too late to work on these problems. Plenty of people are working on these problems, and we can be part of the solution.”
Data science is one way Sim sees herself contributing to the solution. Watersheds generate enormous amounts of data, but data alone doesn't restore a stream or protect a salmon run. The quality, accessibility, and usability of that data matter. For Sim, data science can help bridge the gap between monitoring and action - turning complex information into insights that help people understand changing conditions, identify solutions, and make better decisions.
Making those tools and insights accessible is an important part of the work for Sim. She believes technical knowledge shouldn't be siloed or gatekept. By bringing data science, machine learning, and AI into conversation with people across the watershed field, she sees an opportunity to combine different perspectives and find creative solutions to problems that no single discipline can solve alone.
How Did They Get There?
Sim's path started with a Computer Science degree at UBC, followed by experience as a Software Developer before moving into environmental data work. “I wanted to make data more accessible,” a thread that runs through her shift from software into watershed technology.
A pivotal moment came when Sim participated in the Climate Change AI Summer School and saw how machine learning and AI could be applied to climate challenges; applications she hadn't encountered during her undergraduate degree. It opened her eyes to a different path for her technical skills and, when an opportunity arose to work with watershed and climate data, she took it.
Sim didn't come into the field with a background in water, ecology, or hydrology. She brought strong technical fundamentals, curiosity, and a desire to apply her skills to problems with a more direct impact. Her journey shows that technical skills don't have to lead to a traditional tech career; they can be a starting point for exploring new fields, building new knowledge, and finding work that has meaning and impact.
Want to Follow a Similar Path?
“Don't wait until you feel like an expert to start. What matters most is figuring out what skills you already have and where you can apply them, and whatever those skills are, they're valuable.”
Sim’s advice is to build strong fundamentals, stay curious, and resist the pressure to silo yourself into a single role or industry. Look beyond the obvious career path and consider where the skills you already have could contribute to a problem that genuinely matters to you..
Be prepared to embrace the unglamorous work. In data science, some of the greatest value comes not from the exciting modelling or AI, but from building strong data pipelines and working through the messy data that makes everything else possible.
What do Data Scientists do in Watersheds?
A Data Scientist working on watersheds turns complex environmental information into insights that help people make data-informed decisions about the land and water they manage.
That can mean bringing together information from streamflow gauges, water quality samples, satellite imagery, fish counts, precipitation records, and soil data, then using statistics, machine learning, and visualization to uncover patterns and changes that might otherwise be difficult to see. For example, where is erosion risk increasing? How is a restoration project affecting salmon habitat? Which watersheds may be most vulnerable to drought or flooding?
Data Scientists can build models that explore how conditions could change in the future - such as how water temperatures may respond to a changing climate - and develop dashboards and other tools that make complex information easier to visualize, understand, and use.
Much of the work, however, happens before a model or dashboard is ever built. Data can be incomplete, inconsistent, difficult to access, or spread across different sources. Finding, organizing, cleaning, and improving that information is a critical part of the job. Good data science starts with a strong foundation of reliable, usable data that can be turned into meaningful insights.
What’s a Typical Pathway?
There is no single pathway into watershed data science. People may start in quantitative or technology-focused fields such as computer science, statistics, mathematics, or data science, or come from environmental disciplines such as hydrology, ecology, geography, or environmental science.
A bachelor's degree can provide a strong foundation, while some positions may require or benefit from graduate education. Depending on the role, Data Scientists may build skills in programming languages such as Python or R, statistics and machine learning, databases and data management, GIS, remote sensing, and data visualization.
Technical skills are only part of the picture. Understanding the watershed context behind the data helps Data Scientists ask better questions and build more useful tools. This knowledge can be developed over time through coursework, hands-on experience, research, mentorship, and collaboration with watershed specialists.
You don't need to know everything about both technology and watersheds before you begin. Strong fundamentals, curiosity, and a willingness to learn across disciplines can open up many different entry points into the field.
Why Does It Matter?
Watersheds generate enormous amounts of data, but data alone doesn’t restore a stream or protect a salmon run. Its real value comes from being able to trust it, understand it, and use it to make better decisions.
As a changing climate alters the water cycle, shifts growing seasons, changes precipitation patterns, and brings new pressures such as wildfire and drought, data scientists play a critical role in making sense of increasingly complex environmental conditions. Their work can help watershed managers understand current conditions, evaluate whether restoration projects are working, anticipate how watersheds may respond to future stressors, and determine where limited resources can have the greatest impact.
That information can support decisions about where to focus monitoring, restoration, stewardship, and other limited resources. By helping turn complex data into accessible, usable information, Data Scientists provide an important bridge between what we know about our watersheds and what we choose to do about it.