Hello everyone! I’m Melody Hageman, and I teach science and computer science. I’ve been working with Project GUTS to help students learn how to use models in scientific inquiry. Today, we’re going to dive into how models and simulations can be powerful tools in science.
Models are like simplified versions of the real world that help us study complex things. When we create a model, we focus on the important parts and leave out the details that aren’t necessary for our study. In computer science, this process is called abstraction.
For example, if you build a model of the solar system using styrofoam balls, you’re simplifying the real solar system. Similarly, a computer model is a digital version that can be programmed to act like the real thing. It captures the key elements and behaviors of what we’re studying.
Once we have a computer model, we can run simulations. This means we use the model to mimic how a system behaves over time. It’s like doing an experiment in a lab, where you observe, collect data, and make predictions based on what you see. Each time you run a simulation, you gather data and analyze it, just like in a real experiment.
There are many reasons to use simulations instead of real-life experiments. Once you have a model, you can run it multiple times with different settings to explore various scenarios. If you need to add something to the model, you can easily modify it. Running simulations mainly costs time, not physical resources.
Simulations are also useful when real experiments are too difficult, dangerous, or expensive. For example, studying genetic changes in certain animals might be impractical in a traditional lab setting.
Models can be deterministic or stochastic. A deterministic model gives the same result every time for a set of inputs, with no randomness. A stochastic model, on the other hand, can give different results for the same inputs because it includes randomness. The models we’ll use in our studies are stochastic, meaning they can produce a range of possible outcomes. This is why it’s important to run these models multiple times to see different results.
Both lab experiments and computational experiments involve controlling variables to understand cause-and-effect relationships. In computational science, we use abstraction to focus on what’s important. We can also change how components behave, which is often not possible in real life. Computational experiments can be automated, making them quick and accurate, while real-life experiments might have human errors.
Observing the real world can lead to forming hypotheses. In computational experiments, you might test all possible variables, known as the parameter space, to find patterns and develop hypotheses, instead of starting with one.
I hope this introduction to using computer models in scientific inquiry helps you see why models and simulations are such valuable tools in modern science!
Design a simple model of a real-world system using everyday materials. For example, use balls and strings to represent the solar system. Focus on capturing the key elements and behaviors of the system. Present your model to the class and explain how it simplifies the real-world system.
Use a computer simulation tool to model a natural phenomenon, such as weather patterns or population growth. Run the simulation multiple times with different parameters and record the outcomes. Analyze the data to identify patterns and discuss how changing variables affects the results.
Take an existing computer model and modify it to include a new variable or change a behavior. Document the changes you made and run simulations to see how the modifications affect the outcomes. Share your findings with the class and discuss the importance of flexibility in modeling.
Explore the differences between deterministic and stochastic models by creating simple examples of each. For instance, use a dice roll to demonstrate randomness in a stochastic model. Compare the results and discuss why different types of models are used in scientific inquiry.
Conduct a simple real-world experiment, such as measuring plant growth under different light conditions, and compare it with a computational simulation of the same experiment. Discuss the advantages and limitations of each approach and how they complement each other in scientific research.
Sure! Here’s a sanitized version of the transcript:
—
Hi everyone, I’m Melody Hageman, a science and computer science teacher. I’ve been working with Project GUTS to help students explore using models in scientific inquiry for several years. In this presentation, we’re going to explore how to use models and simulations in scientific inquiry.
The beauty of developing models is that they can serve as virtual test beds for performing experiments and exploring phenomena of interest. But first, what is a model? A model is a simplification of what we want to examine. When we create a model, we ignore some details and focus on what is important at the time. In computer science, we refer to this simplification as abstraction.
For example, building a model of a solar system using styrofoam balls is a simplification of the real solar system. Similarly, a computer model is a simplification or abstraction of what we’re trying to study. Unlike the physical model, once we’ve created a computer model, we can program it to behave like the real thing. A computer model can capture the elements and behaviors of what we want to study.
Once the computer model is created, we can use it for simulations, which involves running the model we’ve developed. We run the model to simulate the passage of time and explore the behavior of the modeled system. This is similar to running an experiment in a lab, where students observe behavior, collect and analyze data, and develop explanations or predictions based on evidence. Each time we run the model, we observe behavior, gather data, and make interpretations or calculations from that data. Thus, running a simulation is akin to performing an experiment on your computer.
Why would you want to run simulations on your computer instead of real experiments in the lab? There are many reasons. Once you develop a model, you can run it multiple times with different variables or parameters, allowing for thorough exploration. If you realize you’ve left something important out, you can modify the model to include it. After the model is developed, running simulations primarily costs time, not resources.
Additionally, you can develop models for situations where experimentation is too difficult, dangerous, impossible, or expensive. For example, exploring genetic drift in certain mammals may be impractical through traditional experimentation.
Models can be classified in various ways. One way is to categorize them as deterministic or stochastic. A deterministic model provides only one output for a set of inputs, with no randomness involved. In contrast, a stochastic model can produce different outputs for the same inputs due to the presence of randomness. The agent-based models of complex adaptive systems we will use in our curriculum are stochastic and produce a distribution of possible outcomes. Repetition is crucial when using a stochastic model, as different results may emerge from the same input variables.
There are similarities and differences between lab experiments and computational science experiments. Both involve controlled experimental designs to produce evidence of causal relationships by isolating variables. In computational science, we can use abstraction to focus on important factors and components. We can also change the underlying behavior of components, which is rarely possible in real life. Additionally, computational science allows for automation to repeat experiments quickly and accurately, while real-life experiments may be affected by human error.
Manipulations and observations of the real world can lead to hypothesis building. Your experimentation might involve testing the entire space of variables, known as the parameter space, to look for patterns that may lead to hypotheses, rather than starting with a hypothesis.
I hope this introduction to using computer models in scientific inquiry has provided insight into why models and simulations are valuable tools in modern scientific research.
—
This version maintains the core content while removing informal language and ensuring clarity.
Models – Representations or simulations of real-world processes or systems used to understand and predict their behavior. – Scientists use climate models to predict future changes in Earth’s weather patterns.
Simulations – Computer-based programs that mimic real-world activities or processes to study their behavior under different conditions. – The flight simulation helped the students understand how pilots train for various weather conditions.
Computer – An electronic device that processes data and performs tasks according to a set of instructions called programs. – The computer in the lab is used to analyze large sets of scientific data.
Science – The systematic study of the structure and behavior of the physical and natural world through observation and experiment. – In science class, we learned about the laws of motion and how they apply to everyday life.
Data – Information collected during experiments or observations, often used for analysis and decision-making. – The data from the experiment showed a clear correlation between temperature and reaction rate.
Experiments – Controlled procedures carried out to test hypotheses and observe outcomes in scientific research. – The chemistry experiments helped us understand how different substances react with each other.
Variables – Factors or conditions that can change and affect the outcome of an experiment. – In our biology experiment, we kept all variables constant except for the amount of sunlight the plants received.
Stochastic – Processes that are random or probabilistic in nature, often used in modeling and simulations. – The weather forecast model includes stochastic elements to account for unpredictable changes in atmospheric conditions.
Deterministic – Processes that are predictable and follow a set pattern or rules, with no randomness involved. – The deterministic algorithm always produces the same result when given the same input.
Inquiry – The process of asking questions and seeking answers through investigation and research. – Scientific inquiry involves forming a hypothesis and conducting experiments to test it.
