Education and AI: How science can facilitate learning artificial intelligence

The integration of artificial intelligence (AI) in education presents exciting opportunities to enrich learning experiences and prepare students for a future where these tools will play an increasingly vital role. However, two key challenges arise. First, the educational community has not yet developed a pedagogy that helps students understand and fully harness the vast potential of AI. Second, there is ongoing uncertainty about how to incorporate AI in a way that fosters, rather than undermines, the development of critical thinking and student autonomy.

We believe a compelling way to tackle these challenges is by combining hands-on science experiments with AI exploration. This approach allows students to engage with AI while simultaneously learning new scientific concepts. Science offers an ideal context to harness the power of modern generative models. Already used by researchers to accelerate their work, AI can enhance every stage of scientific inquiry—from literature review and data analysis to modeling and presenting results. In a practical experimental setting, AI not only sparks excitement but also broadens educational opportunities.

In the sections that follow, we invite you to join us in this experiment and discover what could be the interactions between students and AI, offering fresh insights into how AI's generative models can be integrated into educational practices.

An inquiry-based method boosted by AI

The inquiry-based method is based on the idea that students learn most effectively by being active and exploring on their own, rather than passively receiving information. In this method, the student uses all the tools at his or her disposal to "investigate" a phenomenon in the manner of a researcher.

Our proposal is to integrate AI into inquiry-based activities to enhance students' investigative capabilities. The aim is for the thoughtful use of AI to encourage students to delve deeper into questioning and the scientific process. With AI tools at their disposal, their potential for exploration and discovery is significantly expanded. The scientific method is strengthened as students can focus more on critical thinking and applying their knowledge.

An AI-enhanced scientific investigation could include the following steps:

1. Documentary Research: Students use virtual assistants to efficiently conduct comprehensive research on different aspects of the problem, gaining a deeper understanding of the topic.

2. Experimentation: AI guides students in selecting the best instruments and avoiding common mistakes during the experimental phase.

3. Data Analysis: Through dialogue with AI, students analyze their data, identify patterns or anomalies, and visualize their findings graphically.

4. Modeling: AI assists students in refining a theoretical model based on their observations and experimental data.

5. Model Study and Discussion: Students use AI to explore the model's behavior under various conditions, including boundary values, and assess its sensitivity to different parameters.

6. Applications and Innovation: AI’s extensive databases help students discover real-world applications and potential innovations related to their findings.

7. Conclusions and Communication: Students collaborate with AI to produce a clear, logical, and coherent report of their investigation.

8. Sharing: Together, the student and AI determine the most effective way to structure and share the findings.

   
   

The educational objective of this session is to show students how AI can enhance their research, help them organize their work, initiate productive dialogues, and recognize both the strengths and limitations of these tools. Ultimately, the goal is to help students learn how to leverage AI to its fullest potential.

Experimental Focus and Practical Implementation

In this article, we propose a scientific investigation on a physical phenomenon that is straightforward for students to implement, yet complex enough for AI to play a meaningful role. This practical work is designed for 11th grade students specializing in "Physics-Chemistry" or "Engineering Sciences." The complexity of the chosen phenomenon deliberately exceeds the program's typical expectations, aiming to encourage students to seek AI assistance and push beyond their usual limits.

The challenge we present to students is: “By combining an experimental approach and AI, use your smartphone’s accelerometer to study the mechanics of a vertical elastic pendulum and produce a scientific publication.”

The publication should include the essential components of scientific research: literature review, experimental setup, data analysis, modeling and theoretical connections, model study and discussion, applications, and communication.

To carry out the experiment, students are provided with a 40 cm elastic band to serve as a spring, along with a plastic bag to hold the smartphone. This activity can be conducted in the laboratory or classroom, provided suitable spaces are available to hang the pendulums.

For AI support, we use ChatGPT in this article, but any AI system can deliver similar results, and we encourage students to select the platform they prefer. As AI tools are evolving rapidly, additional features may become available. In practice, students can access AI via classroom computers, tablets, or smartphones with the ChatGPT app.

Calibrating the AI tool

Before starting an experimental study, you need to calibrate your instruments. The same goes for AI. This process is called prompting . Prompts are the instructions or questions provided by the user to guide the AI in its response. In other words, a prompt is the starting point that tells the AI what the user wants to get in terms of information or help.

Prompts are used to:

• Guiding responses : A prompt helps the AI understand the context and purpose of the question. For example, a specific and well-formulated prompt helps the AI generate a more relevant and targeted response.

• Set tone and structure : The prompt type can tell the AI what style of response to expect (formal, informative, creative, concise, etc.). A prompt asking for a simple explanation for a high school student, for example, guides the AI toward a more educational and accessible tone.

• Specify actions or formats : Some prompts can ask the AI to structure the response in a specific way (e.g., as a list, paragraph, or worked example). This allows you to receive a response that matches a particular format or requirement.

• Customize results : Prompts allow you to tailor the response to specific needs, such as asking for an explanation tailored to a certain level of knowledge or a specific domain (science, history, technology, etc.).

  
  

To begin work with a generative model, it is therefore important to write an initial prompt that defines the context, the objective of the research, the type of answers that we want to obtain, and the level of complexity of the answers. It is essential that the student and his group, with the help of the teacher, define one or more introductory prompts adapted to the research and the level of the students. The risk if this introductory phase is not followed is that the AI gives results that are too complex or poorly adapted to the level of the students.

By clicking on the > tab below, you can view the prompt we used for the rest of the exercise.

See the Dialogue with ChatGPT

Question: In the following, I am a first year science student and with my group we want to study the vertical movement of a pendulum attached to an elastic band. To do this we will do an experiment to collect the data provided by the pendulum's accelerometer. We are going to ask you questions, be sure to help us but remember that we are only in first year and that the answers must be concise and not too complicated.

Noted! I will be here to help you with simple and concise answers. What is your first question?

Documentary research

Document research using artificial intelligence is the simplest and most common use of generative models. However, within the framework of the scientific investigation method, AI brings important educational advantages.

The aim of the literature review is to provide students with the theoretical foundations needed to understand the swinging pendulum, exploring key concepts such as oscillations, damping, and mathematical modeling. It also prepares them to use modern measurement tools, such as smartphone sensors, and to lay the foundations for the analysis and modeling of experimental data. Finally, it encourages structured scientific thinking before moving on to experimental manipulation.

AI is interesting pedagogically in this context because it allows rapid access to precise information adapted to their specific questions through an interactive dialogue. It guides them in their thinking by suggesting relevant avenues and clarifying complex concepts. AI personalizes learning by adapting to the students' level of understanding, while synthesizing information to allow them to focus on the essentials. By facilitating understanding and guiding research, AI allows students to structure their scientific approach in a more fluid and efficient manner.

By opening the tab > below, you will discover the beginning of a conversation between a student and an AI, which allowed the student to circumscribe the subject and obtain initial hypotheses on the mathematical model of the acceleration of the pendulum.

See the Dialogue with Chat GPT

Question: Why is this pendulum different from the simple pendulum?

The pendulum attached to a rubber band is different from a simple pendulum because the rubber band can stretch and contract. This changes the length of the pendulum as it moves, making its behavior more complex. In a simple pendulum, the length is fixed and the motion is smooth, but with a rubber band, the force varies depending on the stretch, creating a more irregular and non-linear motion.

Question: Which scientists discovered the elastic pendulum?

The concept of the elastic pendulum (or spring pendulum) is not a "discovery" attributed to a single scientist, but rather is the result of an evolution of work on oscillating systems and spring mechanics.

1. Robert Hooke (1635-1703) is often cited as one of the first to lay the theoretical foundations for understanding the behavior of an elastic pendulum, thanks to his Hooke's law , (....).

2. Christiaan Huygens (1629-1695), although best known for his work on the simple pendulum and the pendulum clock, also influenced the study of more complex oscillating systems, such as the spring pendulum. His work on the oscillations (....)

3. Leonhard Euler (1707-1783) and Jean le Rond d'Alembert (1717-1783) contributed to the formulation of differential equations used to model systems such as the elastic pendulum. (...)

The elastic pendulum is therefore the result of the application of several concepts from the work of these scientists on elastic forces and oscillations.

Question: What are the applications of the elastic pendulum?

The elastic pendulum has several applications in various scientific and technological fields:

1. Study of oscillations and dynamic systems : The elastic pendulum is used to study complex oscillations and nonlinear systems, often in advanced physics courses. It helps to understand the forces at play when oscillating systems are subjected to non-constant restoring forces, as in springs or rubber bands.

2. Vibration modeling : The principles of the elastic pendulum are used to model vibrations in many mechanical systems, such as vehicle suspensions, suspension bridges, or skyscrapers subjected to seismic forces.

3. Applications in sensors : Modern sensors, such as accelerometers in smartphones, can be used to analyze the movements of the elastic pendulum.

4. Medicine and biomechanics : In biomechanics, elastic pendulum-based models are used to simulate the movement of muscles and tendons, which often behave like springs during joint movements.

5. Renewable Energy Systems : The elastic pendulum has applications in some energy harvesting systems, such as systems that harness wave or tidal energy.

These examples show how a relatively simple concept can be applied to a wide variety of domains to model complex phenomena.

Question: Are there any scientific papers that explore the study of pendulums with a rubber band and a smartphone?

Yes, there are scientific papers that explore the use of smartphones to study the motion of elastic pendulums. For example, several studies have used a smartphone's accelerometer to analyze pendulum phenomena, including versions with springs or rubber bands. One interesting study used smartphones attached to springs to measure oscillations and obtain motion data, which was then exported to software like Excel for further analysis. They were able to determine important parameters like the spring constant and the frequency of oscillations.

Another paper even introduced the use of LiDAR sensors present in some smartphones for precise distance measurements, in addition to the data provided by the accelerometer, thus improving the accuracy of the results for the study of spring and elastic pendulums. This allows a better understanding of damped oscillations and associated dynamic phenomena.

Question: What is the mathematical equation for acceleration as a function of time?

Question: What other questions should I ask you to do a complete literature search?

To conduct a comprehensive literature search on the elastic pendulum, here are some additional questions to ask, which will allow you to delve deeper into different aspects of the subject:

1. History of the elastic pendulum :

   • What are the first historical works on the elastic pendulum and how have they influenced modern physics?

   • How has the elastic pendulum been used in the history of science?

2. Theoretical and mathematical aspects :

   • What are the main differential equations associated with the movements of an elastic pendulum?

   • What are the differences between linear and nonlinear behavior of the elastic pendulum?

   • How does Hooke's law apply to the motion of the elastic pendulum?

3. Comparison with other oscillating systems :

   • What are the differences between a simple pendulum, a conical pendulum, and an elastic pendulum?

   • What are the similarities and differences between an elastic pendulum and other oscillating systems, such as a simple harmonic oscillator?

4. Modern applications :

   • How are the principles of the elastic pendulum used in the design of architectural structures (eg bridges, buildings) to absorb vibrations?

   • What are the applications of the elastic pendulum in the medical field, for example in the study of the movement of muscles and tendons?

   • How are smartphones and their sensors (accelerometers, LiDAR) used to study the motion of elastic pendulums?

5. Practical experiences :

   • What simple experiments can be performed to study an elastic pendulum, using tools such as a smartphone?

   • How to analyze acceleration and motion data obtained by a smartphone attached to an elastic pendulum?

6. Modeling and simulation :

   • What software is used to model the motion of an elastic pendulum?

   • What are the numerical methods used to simulate the oscillations of an elastic pendulum?

7. Open issues and current research :

   • What are the current challenges in the study of elastic pendulums, particularly in nonlinear mechanics?

   • What research is currently being conducted to better understand the phenomena linked to elastic pendulums?

These questions will help you explore the various theoretical, historical, and practical aspects of the subject, while covering modern applications and current research.

Experimental work

Once the documentary research is completed, the student and his group move on to the experimental manipulations. To succeed in this phase, several elements must be brought together: how to set up the experimental device, the safety rules to follow, record the data and export them for analysis. These aspects can be submitted to the AI to obtain suggestions, adjusted according to the context of the experiment. Below we propose several questions that the student can ask the AI.

It is important to note that AI is not always the ideal solution, which is a valuable learning experience for students. For example, the explanations provided by AI on the experimental setup may lack precision. In this case, the student will have to experiment to find a simple and effective solution on their own. In addition, AI, like ChatGPT, does not always know certain technical specificities, such as the existence of a direct measurement of the norm on FizziQ, which students will discover along the way.

To view the AI chat, tap the > tab below.

See the Dialogue with ChatGPT

Question: Is there any risk in doing this experiment?

Experimenting with a rubber band pendulum is generally safe, but as with any experiment involving physical motion and forces, there are some precautions to take to minimize risk:

1. Falling object : Make sure the object attached to the bungee cord (in this case, a smartphone) is securely fastened. A loose attachment could cause the object to fall, potentially damaging it or injuring someone underneath.

2. Rubber band failure : If the rubber band is not designed to support the weight or tension applied, it may fail. Use a rubber band that is appropriate for the mass of the object and the amplitude of the oscillations expected.

3. Impact with the environment : The oscillating object could collide with other objects or people nearby. Make sure to clear enough space around the experiment area.

4. Unexpected reactions : In the case of very stretchy rubber bands or systems under high tension, movements may be more violent or unpredictable than expected. Always test in a controlled environment before increasing mass or tension.

Question: How to attach the smartphone to the rubber band to improve measurements?

It is important to attach the smartphone securely and symmetrically to the spring or rubber band to avoid interference. Here are some tips:

• Center Position: Secure the smartphone at its center of gravity to ensure its weight is evenly distributed, minimizing unwanted oscillations. Use soft but secure attachments (such as extra rubber bands or Velcro strips) to avoid obstructing the vertical movement of the pendulum.

• Rigid fixation: Ensures that the smartphone is securely held in the spring axis without it being able to slide or swing sideways, as this could introduce unwanted movements.

• Orientation: Positions the smartphone so that the most relevant accelerometer axis is aligned with the vertical axis of motion (usually the z-axis in smartphones), for accurate measurement of vertical accelerations.

• What is the best smartphone to perform these acceleration measurements? For accurate acceleration measurements, it is recommended to use a smartphone equipped with high-quality accelerometer and gyroscope sensors. Recent smartphone models such as the iPhone (iPhone 12 and later) or Samsung Galaxy (S20, S21 and later) range offer excellent accuracy for data collection. These devices have highly sensitive and carefully calibrated motion sensors. In addition, they are compatible with scientific applications such as FizziQ and Phyphox , which provide easy access to sensor data.

  
  

Question: Which application is best for taking measurements?

The two best applications to perform these measurements are FizziQ and Phyphox :

1. FizziQ : Developed specifically for science education, FizziQ allows you to measure and record sensor data in an intuitive way. It offers tools to visualize graphs and interpret data directly via the interface. It is particularly well suited for educational experiments, with a clear and simple user interface.

2. Phyphox : This app is also very popular for scientific measurements. It provides direct access to smartphone sensors and offers a wide range of analysis tools, with the ability to set up complex experiments and customize sensor settings. Phyphox is very flexible and offers real-time data visualizations.

Question: What measurement should I use on FizziQ if I want to measure the acceleration standard on the smartphone?

On FizziQ , if you want to measure the acceleration norm on the smartphone (i.e. the total acceleration combining the xx, yy, and zz axes), you need to use the measurements coming from the accelerometer sensor . While FizziQ may not have an explicit option to calculate the norm directly, here's how to do it:

1. Select the “Accelerometer” sensor:

   • Go to the FizziQ app and select the Accelerometer sensor.

   • This sensor will provide you with acceleration data on the three axes xx, yy, and zz.

2. Export data or calculate manually:

   • If FizziQ does not offer direct measurement of the norm (total acceleration), you can export the data of the three axes xx, yy, and zz in CSV format.

   • Then use a software like Excel to calculate the acceleration magnitude using the following formula: aglobal=ax2+ay2+az2aglobal=ax2+ay2+az2

   • This will allow you to obtain the acceleration norm by combining the three axes.

3. Check the settings in FizziQ:

   • Some versions or configurations of FizziQ may offer an option to directly display the acceleration norm in the GUI. If this option is available, you will not need to do the calculation manually.

Question: How to export data with FizziQ?

With FizziQ , exporting data is quick and easy:

• After taking a measurement, the data is visualized in the application as a graph.

• To export data, simply click on the "Export Data" option (or a dedicated icon). The application offers several export formats, including CSV (tabular data text format).

• You can send this data by email directly from the application, or save it in a storage space on your smartphone (for example Google Drive or Dropbox).

• Then you can open the CSV file in software like Excel or Google Sheets to analyze the data in more detail.

After verifying that the generated graph has enough oscillations, the data is exported to a CSV file. The experimental phase is therefore complete, we can now return to using AI to analyze the data!

Data analysis

Data analysis aims to examine the recorded experimental information to extract key elements and draw conclusions about the physical characteristics of the observed motion. This includes removing unnecessary segments to clean the data, smoothing the data to reduce noise, and identifying features such as the period of the motion or the damping of oscillations.

Modern generative models allow not only in-depth graphical or statistical analysis, but also direct data reprocessing through a natural language interface, which is more intuitive for the student. The student can of course ask for help to perform these operations or understand their usefulness.

Quickly, the student will be able to:

• Visualize data : To obtain a graphical representation that makes it easier to understand trends.

• Clean the data : By eliminating anomalies or outliers that could distort the analysis.

• Smooth data : To smooth out random fluctuations and better see major trends.

• Calculate and interpret characteristics : How to determine the period of oscillations and evaluate the effectiveness of damping.

• Export data : To use in other software or share.

In our dialog below, we analyzed and cleaned the data coming from the table exported in the experimental part. This analysis revealed important aspects of the behavior of acceleration over time and allowed us to detect invariants in the motion.

Open the > tab to discover the dialogue between the student and the AI

See the Dialogue with ChatGPT

Question: Make the graph of the attached data in CSV file

Here is the graph of absolute acceleration over time, based on the data you provided. This plot shows the fluctuations in absolute acceleration. If you want to make changes or need further analysis, let me know!

Question: In this graph remove the data before the lowest point and after 10 s

Here is the absolute acceleration graph filtered to show data between about 2.3 seconds and 10 seconds. This shows you the fluctuations in acceleration during that specific period. If you need more adjustments or other analysis, feel free to ask.

Question: Smooth the data so I can better observe the phenomenon

Question: What is the period of the phenomenon?

After smoothing the data and calculating the periods between peaks and troughs, the average period of the phenomenon, on the smoothed data, is about 0.69 seconds. This calculation is based on both peaks and troughs, which give very close values, confirming the regularity of the observed phenomenon. If you have any further questions or need additional analysis, I am here to help you!

Question: Is the period stable?

The mean period is about 0.69 seconds, with a standard deviation of 0.015 seconds. This indicates that the period is relatively stable, with small variations around the mean. The fluctuations are minimal, suggesting that the observed phenomenon is regular.

If you need more details or additional analysis, please let me know!

Question: Can you study the damping of oscillations?

To characterize the damping of the amplitude of oscillations more quantitatively, we can use a regression approach to estimate how the amplitude of the peaks decays over time. A common approach is to fit an exponential decay function, typically used to model damping in oscillating systems.

I will fit an exponential model to the peak amplitudes and show you the results.

The exponential decay fit to the peak amplitudes does indeed show a damping of the oscillations. The fit parameters are as follows:

• A≈15.04A≈15.04: initial amplitude.

• B≈0.273B≈0.273: decay rate.

• C≈9.99C≈9.99: asymptotic value towards which the amplitude tends.

The red curve on the graph represents the exponential decay fit, and it is clear that the peak amplitudes decrease with time, indicating a noticeable damping of the oscillations.

Exports the smoothed data into a table

The smoothed data has been exported to an Excel table. You can download it by following this link: Download the Excel file.

If you need any further adjustments, please don't hesitate to ask!

Modeling

In scientific reasoning, the relationship between theory, model, and data can be articulated in several ways, each reflecting a different approach to research. A direct method is to start with theory and verify that experimental data confirm the mathematical equations derived from it. It is also possible to construct a mathematical model that seems to explain the data well, in order to guide theoretical thinking in a specific direction. Both of these approaches can be facilitated by the use of artificial intelligence.

In our example, during their documentary research, the students were directed towards a periodic sinusoidal evolution of the acceleration. By analyzing the curves, they also observed that, although this evolution is periodic, the amplitude of the oscillations seems to decrease with time. These observations are transmitted to the AI to try to determine a model that explains the data, and to obtain indications on the theoretical reasons explaining this model.

To view the AI chat, open the > tab below.

See the Discussion with ChatGPT

Question: Use the smoothed data and try to see if the mathematical model you mentioned can explain this data?

To check whether the model I mentioned (based on an elastic pendulum) can explain these data, we will compare the experimental data to a theoretical acceleration model, taking into account the equation of motion of the elastic pendulum.

I will fit a theoretical model to your data and see how they match. I will first try to fit a function based on a damped oscillation, typical of an elastic pendulum, and see how it compares to your measurements.

The damped oscillation model fitted to the experimental data gives the following parameters:

• Amplitude (A) : 15.78

• Damping factor (gamma) : 0.26

• Angular frequency (omega) : 9.09 rad/s

• Initial phase (phi) : -8.23 rad

• Vertical offset : 9.83

The graph shows a good match between the measured data and the theoretical model, suggesting that the observed motion can be well described by a damped oscillation, typical of an elastic pendulum.

If you want to explore the data further or modify the model, let me know!

Question: It seems to fit well, right?

Yes, the damped oscillation model seems to fit the measured data well, indicating that the behavior of the elastic pendulum you observed does indeed follow damped oscillation dynamics. This means that the forces involved, such as stretching of the rubber band and damping due to friction or energy dissipation, are well accounted for by this model.

If you would like to explore further or test other models or scenarios, please feel free to ask further questions!

Question: How can I explain this acceleration equation simply?

To explain the equation for the acceleration of the elastic pendulum in a simple way, we can say:

1. Amplitude (A) : This is the initial force or extent of the movement. The greater the amplitude, the faster the pendulum moves at the beginning.

2. Damping factor (γ) : This is the gradual decrease in the speed of the pendulum due to friction or resistance. This causes the oscillations to become smaller and smaller over time.

3. Angular frequency (ω) : This is the speed at which the pendulum oscillates. It depends on the stiffness of the elastic and the mass of the pendulum.

4. Phase (ϕ) : This is the starting position of the pendulum in its motion. This affects where it is at the moment we begin observing.

5. Offset : This is the base value around which the oscillation occurs. Here, it can be a kind of "base level" of acceleration.

In short, this equation says that the acceleration of the pendulum decreases over time due to damping, while swinging around a central position, following a progressively slowing motion.

Question: I have trouble understanding, I am a first year student, can you explain better why the acceleration follows such a mathematical function?

We see through these exchanges that AI can adapt to the level of the person it is exchanging with. For a first-year student, the explanation is much clearer. It can be even simpler if necessary.

Model analysis

The purpose of the model study is to analyze the behavior of the determined theoretical model. In the context of our study, the student seeks to understand how different parameters of the system – such as the damping or elasticity of an elastic band – influence the oscillations of an elastic pendulum . Some of these parameters can only be discovered after several round trips in the questioning, a process that contributes to the student's learning.

This study often requires the creation of a computer program to generate curves and facilitate the exploration of parameter variations. AI is an excellent programming assistant and can help the student in this creation process. The tool can also perform these analyses online, using natural language.

To discover the exchange between the student and the AI, open the dialog box > below:

See the Dialogue with ChatGPT

Question: Using the model, plot the curves for 10 seconds between an elastic band with the same characteristics as our elastic band, an elastic band without damping, and an elastic band with double damping.

Here is the extended simulation for 20 seconds, showing the behaviors of the three types of rubber bands:

• Red (Extended Damped Model) : Shows a continuous decrease in oscillation amplitude due to damping.

• Green (Ideal model without extended damping) : Exhibits constant amplitude oscillations, indicating perpetual motion without energy loss.

• Purple (Extended Damping Double Model) : The amplitude of the oscillations decays more quickly than in the standard damping model, illustrating the effect of stronger damping on how quickly the system's energy is dissipated.

This visualization helps to understand the fundamental differences between a system with and without damping, and how increasing damping impacts the motion of an elastic pendulum over an extended period.

Question: Now draw the curves between a very little stretchy elastic and a very stretchy one and ours.

Here are the curves for three different levels of elastic stretch:

• Blue (Normal Elasticity) : This is our reference model showing oscillation with standard damping.

• Green (Less Stretchy) : This model represents a less stretchy (stiffer) rubber band. Oscillations are faster due to a higher angular frequency, indicating greater stiffness.

• Red (More stretchy) : Here the rubber band is more stretchy (less stiff), so the oscillations are slower with a reduced angular frequency, reflecting lower stiffness.

These curves illustrate well how the stiffness of the rubber band influences the dynamics of the system, affecting the frequency of oscillations. A stiffer rubber band reacts more quickly, while a softer one shows more extended oscillations in time.

Question: I see that the period changes, what is the influence of the elasticity of the rubber band on the period?

The period of oscillation of an elastic pendulum is directly influenced by the elasticity (or stiffness) of the rubber band used. This relationship is defined by the physical properties of the rubber band, particularly by the spring constant kk and the suspended mass mm. Here is how elasticity affects the period of an elastic pendulum:

1. Spring Constant (k) : The spring constant kk of a spring measures how difficult it is to stretch or compress the spring. The higher kk, the stiffer the spring.

2. Mass (m) : The mass suspended from the spring also affects the period of oscillations. The heavier the mass, the longer the period of oscillations, because it takes longer for the spring to stretch or compress under the effect of this mass.

3. Period Formula : The period TT of oscillations for an elastic pendulum (mass-spring system) is given by the formula:

   T=2π √ (m/k)

   
   

   This formula shows that the period is proportional to the square root of the mass and inversely proportional to the square root of the stiffness constant.

   • More extensible : If the elastic is more extensible (less rigid, therefore kk smaller), this increases the period of the oscillations, because the system is less likely to return to its equilibrium position.

   • Less Extensible : If the rubber band is less extensible (more rigid, therefore kk is larger), this decreases the period of the oscillations, because the system returns more quickly to its equilibrium position.

In summary, the stiffer the rubber band, the shorter the period of the oscillations, and conversely, the softer the rubber band, the longer the period. This relationship is crucial for understanding how different types of springs or rubber bands influence motion in practical applications, such as in shock absorbers or suspension systems.

Question: To be able to do these calculations alone, can you write a python program that allows me to enter the model parameters and obtain a curve of the evolution of the acceleration over 10 seconds?

Communication

Writing a research paper is probably the best-known part of generative model applications. AI can help a student write a well-structured, coherent, and audience-friendly research paper by providing support throughout the writing process.

1. Structuring the document

2. Clarity and fluidity

3. Advice on adapting to the public

4. Reminder of things not to forget

5. Consistency in argumentation and scientific reasoning

6. Final check and proofreading

List of questions for ChatGPT

Document structure :

• “Can you provide me with a complete and logical structure for my scientific research paper?”

Introduction :

• “How can I write a clear introduction that presents my research topic and my initial hypotheses?”

Clarity and fluidity :

• "Can you rephrase this passage to make it clearer and easier to understand for a first-year science audience?"

Explanation of the results :

• “How can I explain the results of my experiment simply while remaining scientifically accurate?”

Adaptation to the public :

• “How can I adapt the complexity of my explanations for an audience of first-year students?”

Discussion of results :

• “What points should I include in the discussion to properly relate my results to the theory being studied?”

Reminder of important elements :

• “Did I miss any important steps in my scientific approach that I should include in the paper?”

Consistency of the argument :

• “Are my hypotheses, results and conclusion well connected in a coherent way?”

Improved conclusion :

• “How can I improve the conclusion so that it summarizes my findings well and emphasizes their scientific importance?”

Final check and proofreading :

• “Can you proofread the entire document to correct mistakes and improve the style?”

Sharing

Students will likely be interested in another aspect of research which is its dissemination. AI can greatly facilitate the dissemination of a research paper and optimize its online visibility through SEO (Search Engine Optimization) techniques.

AI will be able to guide the student for these different tasks:

1. SEO Optimization : AI suggests relevant keywords, writes optimized title tags and meta descriptions, and checks keyword density to improve SEO on Google.

2. Creating titles and subtitles : She reformulates titles and subtitles to make them more catchy and optimized for SEO.

3. Summary writing : AI produces impactful and suitable summaries for social networks or newsletters, thus attracting readers.

4. Content for social networks : It generates specific posts for each platform (Twitter, LinkedIn, Facebook), ensuring optimal distribution.

This part of the work also allows the student to reflect on how search engines provide their answers.

List of questions to ChatGPT

Google search:

• "How does Google choose which sites to display following a query?"

• “How can I improve the online visibility of my article on Google?”

Choosing relevant keywords :

• “What keywords should I use to optimize my article for search engines?”

SEO tag optimization :

• "Can you suggest a title tag (less than 70 characters) and a meta description (less than 300 characters) for my article?"

• “How do I write a good meta description so my article gets more clicks on Google?”

Creating attractive titles and subtitles :

• “How can I make my headlines more impactful to readers and search engines?”

Writing summaries and abstracts :

• “How to write an attention-grabbing summary?”

Creation of content for social networks :

• “Can you write a post for Twitter and Facebook to promote my article?”

Final SEO Check :

• “Is my article well optimized to appear in search results?”

Optimizing content for different audiences :

• “How can I adapt my text for different audiences?”

Conclusion

In this article, we have proposed a practical and motivating approach to introduce students to the vast possibilities offered by generative models, by integrating artificial intelligence (AI) into scientific practical work (TP).

This method seems particularly suitable for introducing students to the use of AI in a school setting. By integrating it into an experimental research context, it encourages an open and exploratory approach, where students can discover and use this tool independently. The sciences offer a particularly fertile ground for this approach, because AI can be used at different stages: documentary research, data manipulation and visualization, theoretical analysis, program creation, as well as communication and dissemination of results. The natural language interface simplifies scientific work, making complex concepts more accessible and allowing students to manipulate them intuitively. In addition, the ability of AI models to adapt to students' objectives and level, thanks to personalized instructions (prompts), makes it an ideal tool for a wide variety of users.

We welcome your feedback on this experience. AI should not be seen as a definitive solution, but rather as a catalyst for reflection and innovation. It helps students not only master science, but also develop essential digital skills for the 21st century. The challenge now is to find a balance between exploiting this promising technology and maintaining the intellectual autonomy of learners, in order to develop critical minds capable of using these tools in an informed and responsible manner.