An Investigation into the Utility of Large Language Models in Geotechnical Education and Problem Solving
Abstract
:1. Introduction
- Interactive tutoring where LLMs offer personalised instruction to enhance student understanding of complex topics, such as soil mechanics and foundation design.
- Virtual lab developing where LLMs are combined with virtual reality. Students can perform virtual soil tests and experiments, with real-time guidance and results interpretation from the LLM.
2. Dataset
2.1. Data Selection
- A large population from which the sample is drawn, and the sample itself represents a minor fraction (less than 5%) of the total population;
- The expected outcome has been simplified to a binary variable—the success or failure of the LLM in problem-solving tasks—which aligns with the typical dichotomous nature of the assessment outcomes;
- The proportion’s sampling distribution is presumed to be normal or approximately normal. This assumption is reasonable for the calculated sample size, invoking the central limit theorem to justify the normal approximation.
2.2. Data Categorisation
2.2.1. Categorisation by Topic
2.2.2. Categorisation by Cognitive Complexity
3. Experimental Setup
- Zero-shot learning: This approach assesses GPT-4’s baseline problem-solving skills without prior exposure to specific examples. It evaluates the model’s ability to leverage pre-trained knowledge and innate reasoning capabilities.
- CoT: In this approach, we prompted GPT-4 to detail its reasoning steps, akin to a human’s approach to problem-solving. This approach aids in understanding the model’s thought process and checks for logical coherence.
- Custom instructional prompting: This technique proactively mitigates common errors and refines GPT-4’s responses. Initially, we conducted a thorough analysis to identify the most frequent and impactful errors that GPT-4 encounters when tackling geotechnical problems. Armed with this insight, we crafted precise prompts containing targeted instructions addressing these shortcomings. These custom prompts were then used to guide GPT-4’s problem-solving process, optimising its accuracy and relevance in response to geotechnical questions.
4. Results
4.1. Accuracy and Effectiveness of Prompting Strategies
4.1.1. Different Topics
4.1.2. Difficulty Level According to Bloom’s Taxonomy
4.1.3. Question Type
4.2. Error Type Distribution
4.2.1. Different Topics
4.2.2. Difficulty Level According to Bloom’s Taxonomy
5. Discussion
5.1. Insights and Implications for Geotechnical Education
- Errors and Problem Complexity: We observed a direct correlation between the complexity of geotechnical problems and the increase in errors from GPT-4. This trend underscores the model’s challenges in processing and accurately responding to more complex tasks, indicating a potential area for future AI development and customised training.
- Text-Based versus Image-Based Questions: GPT-4 exhibits proficiency in handling text-based queries, reflected in a lower occurrence of “Conceptual” errors. However, the performance of the version of GPT 4 used in image-based questions is limited due to an inherent inability to process or interpret images for geotechnical problems. This observation calls for integrated multimodal AI systems that can handle a variety of data formats.
- Deficiencies and Limitations: Despite its strengths in processing textual information, GPT-4 exhibits notable deficiencies in tasks requiring interpreting images or generating complex visual representations. This limitation is particularly pronounced when the flow net diagrams are involved. The model struggles with creating or interpreting such visual content and occasionally fails to adhere strictly to the custom instructions provided. These shortcomings highlight two key areas in need of further development. First, there is a pressing need to enhance GPT-4’s spatial and visual processing capability, enabling it to handle tasks beyond text-based information. Second, the model’s occasional deviation from custom instructions underscores the ongoing requirement for refinement in its ability to understand and process user-specific directives accurately. Addressing these limitations is critical for advancing AI technologies like GPT-4 to improve their effectiveness as educational tools in geotechnical engineering and expand their applicability in solving complex, visually oriented problems.
- Custom Instructions for Enhanced Accuracy: The application of tailored instructions has been shown to significantly improve the accuracy of GPT-4. The improvement is particularly notable in reducing “Conceptual” and “Grounding” errors and mitigating “Calculation” errors in tasks requiring numerical and logical reasoning. This aspect demonstrates the importance of context-specific guidance in enhancing AI performance in educational settings.
5.2. Demonstration of GPT-4’s Question Generation Capabilities in Geotechnical Education
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
US sieve no. | Mass of soil retained |
4 | 28 |
10 | 42 |
20 | 48 |
40 | 128 |
60 | 221 |
100 | 86 |
200 | 40 |
Pan | 24 |
US sieve no. | Mass of soil retained | Cumulative mass retained | Percent finer (%) |
4 | 28 | 28 | 95.46 |
10 | 42 | 70 | 88.65 |
20 | 48 | 118 | 80.88 |
40 | 128 | 246 | 60.13 |
60 | 221 | 467 | 24.31 |
100 | 86 | 563 | 10.37 |
200 | 40 | 593 | 3.89 |
Pan | 24 | 617 | 0.00 |
- Calculate the Total Mass: Sum all the mass retained on each sieve and in the pan to get the total mass of the soil sample.
- Calculate the Mass Passing: For each sieve, determine the mass of soil that passes through by subtracting the cumulative mass retained up to and including that sieve from the total mass.
- Calculate the Percent Finer: For each sieve, calculate the percent finer than that sieve by dividing the mass passing by the total mass and then multiplying by 100.
- Plot the Grain-Size Distribution Curve: Plot the percent finer on the y-axis against the sieve size on the x-axis.
- US sieve no. 4: Mass retained = 28 g
- US sieve no. 10: Mass retained = 42 g
- US sieve no. 20: Mass retained = 48 g
- US sieve no. 40: Mass retained = 128 g
- US sieve no. 60: Mass retained = 221 g
- US sieve no. 100: Mass retained = 86 g
- US sieve no. 200: Mass retained = 40 g
- Pan: Mass retained = 24 g
US Sieve No. | Mass Passing (g) | Percent Finer (%) |
4 | 589 | 95.46 |
10 | 547 | 88.65 |
20 | 499 | 80.88 |
40 | 371 | 60.13 |
60 | 150 | 24.31 |
100 | 64 | 10.37 |
200 | 24 | 3.89 |
Pan | 0 | 0.00 |
- 1.
- Calculate the Percent Retained on Each Sieve: This is the mass of soil retained on each sieve as a percentage of the total mass.
- 2.
- Calculate the Percent Finer than Each Sieve: This is calculated by subtracting the cumulative percent retained up to that point from .
- 3.
- Convert U.S. Sieve Numbers to Standard Sieve Sizes: This is done using a conversion table that correlates U.S. Sieve numbers to millimetre openings.We will perform these calculations and create the table with the following columns: U.S. Sieve Number, Sieve Size (mm), Mass of Soil Retained (g), Percent Retained on Each Sieve, and Percent Finer. Here is the completed table with US sieve numbers, corresponding standard sieve sizes in millimetres, the mass of soil retained on each sieve, percent retained on each sieve, and percent finer:
U.S. Sieve No. | Sieve Size (mm) | Mass of Soil Retained (g) | Percent Retained on Each Sieve (%) | Percent Finer (%) |
4 | 4.75 | 28 | 4.54 | 95.46 |
10 | 2.00 | 42 | 6.81 | 89.63 |
20 | 0.85 | 48 | 7.78 | 75.69 |
40 | 0.425 | 128 | 20.75 | 39.87 |
60 | 0.25 | 221 | 35.82 | 19.12 |
100 | 0.15 | 86 | 13.94 | 11.35 |
200 | 0.075 | 40 | 6.48 | 4.54 |
Pan | 0 | 24 | 3.89 | 0.00 |
- The moisture content or 0.26 in decimal,
- The degree of saturation or 0.72 in decimal,
- The moist unit weight ,
- The unit weight of water ,
- Moisture content () = 26% or 0.26
- Degree of saturation () = 72% or 0.72
- Moist unit weight () = 16.98 kN/m3
- Specific Gravity of Soil Solids (): 1.73
- Void Ratio (e): 0.263
- Moisture content (in fraction)
- Degree of saturation (in fraction)
- Moist unit weight
- Void ratio is given by:
- 2.
- Degree of saturation (S) is given by:
- Saturated unit weight () = 19.8 kN/m3
- Moisture content () = 17.1% or 0.171
- Dry Unit Weight (): 18.12 kN/m3
- Specific Gravity of Soil Solids (): 2.02
- Void Ratio (): 0.093
- Count the number of flow channels (Ni) and equipotential drops (Nd) from the flow net.
- Use Darcy’s Law to calculate the seepage loss, with the formula .
- Convert the seepage loss to by using the following conversion:
- Draw a Flow Net: A flow net consists of flow lines and equipotential lines. Flow lines represent the path that water particles follow as they move through the soil, and equipotential lines are lines connecting points of equal hydraulic head.
- Determine the Number of Flow Channels (Nf): This is the number of flow lines from the entry to the exit of the flow region.
- Determine the Number of Equipotential Drops (Nd): This is the number of equipotential drops from the upstream to the downstream side.
- Calculate the Hydraulic Gradient (i): It is the head loss per unit length of flow. The head loss is the difference in hydraulic head between two equipotential lines, and the length of flow is the perpendicular distance between two flow lines.
- Use Darcy’s Law to Calculate Seepage: Darcy’s law in the form of Q = kiA can be used, where Q is the discharge, k is the hydraulic conductivity, i is the hydraulic gradient, and A is the cross-sectional area through which flow occurs.
- Drawing Flow Lines and Equipotential Lines: Flow lines should curve to intersect the impermeable boundaries at right angles, and the equipotential lines should intersect the flow lines at right angles as well.
- Calculating the Seepage Loss: Once we have the flow net, we can determine Nf and Nd, and then use the values of k (given as 0.002 cm/s) and the dimensions of the permeable layer to calculate the seepage loss.
- Identify entry and exit points for water in the permeable layer.
- Draw flow lines starting from the water entry point, curving and ending at the water exit point. These lines represent the path of water through the permeable material.
- Draw equipotential lines starting from the upstream side (high head) to the downstream side (low head). The first equipotential line is at the upstream face where the head is maximum, and the last equipotential line is at the downstream face where the head is minimum.
- The number of flow channels, Nf
- The number of equipotential drops, Nd
- The length of the flow path, 𝐿 (in meters)
- The difference in head, Δℎ, from the upstream to downstream (in meters)
References
- Bahroun, Z.; Anane, C.; Ahmed, V.; Zacca, A. Transforming Education: A Comprehensive Review of Generative Artificial Intelligence in Educational Settings through Bibliometric and Content Analysis. Sustainability 2023, 15, 12983. [Google Scholar] [CrossRef]
- Rane, N.; Choudhary, S.; Rane, J. Education 4.0 and 5.0: Integrating Artificial Intelligence (AI) for Personalized and Adaptive Learning. SSRN Electron. J. 2023. [Google Scholar] [CrossRef]
- Tan, S. Harnessing Artificial Intelligence for Innovation in Education. In Learning Intelligence: Innovative and Digital Transformative Learning Strategies: Cultural and Social Engineering Perspectives; Springer Nature: Singapore, 2023; pp. 335–363. [Google Scholar]
- Erduran, S. AI is transforming how science is done. Science education must reflect this change. Science 1979, 382, 2023. [Google Scholar] [CrossRef] [PubMed]
- Dwivedi, Y.K.; Kshetri, N.; Hughes, L.; Slade, E.L.; Jeyaraj, A.; Kar, A.K.; Baabdullah, A.M.; Koohang, A.; Raghavan, V.; Ahuja, M.; et al. So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. Int. J. Inf. Manag. 2023, 71, 102642. [Google Scholar] [CrossRef]
- Bandi, A.; Adapa, P.V.S.R.; Kuchi, Y.E.V.P.K. The Power of Generative AI: A Review of Requirements, Models, Input–Output Formats, Evaluation Metrics, and Challenges. Future Internet 2023, 15, 260. [Google Scholar] [CrossRef]
- García-Peñalvo, F.J.; Vázquez-Ingelmo, A. What Do We Mean by GenAI? A Systematic Mapping of The Evolution, Trends, and Techniques Involved in Generative AI. Int. J. Interact. Multimed. Artif. Intell. 2023, 8, 7–16. [Google Scholar] [CrossRef]
- OpenAI. GPT-4 Technical Report. arXiv 2023, arXiv:2303.08774. [Google Scholar]
- Noy, S.; Zhang, W. Experimental evidence on the productivity effects of generative artificial intelligence. Science 1979, 381, 2023. [Google Scholar] [CrossRef]
- Epstein, Z.; Hertzmann, A.; Akten, M.; Farid, H.; Fjeld, J.; Frank, M.R.; Groh, M.; Herman, L.; Leach, N.; Mahari, R.; et al. Art and the science of generative AI. Science 1979, 380, 2023. [Google Scholar] [CrossRef]
- Epstein, Z.; Hertzmann, A.; Herman, L.; Mahari, R.; Frank, M.R.; Groh, M.; Schroeder, H.; Smith, A.; Akten, M.; Fjeld, J.; et al. Art and the science of generative AI: A deeper dive. arXiv 2023, arXiv:2306.04141. [Google Scholar]
- Mao, J.; Chen, B.; Liu, J.C. Generative Artificial Intelligence in Education and Its Implications for Assessment. TechTrends 2024, 68, 58–66. [Google Scholar] [CrossRef]
- Franceschelli, G.; Musolesi, M. Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges. J. Artif. Intell. Res. 2024, 79, 417–446. [Google Scholar] [CrossRef]
- Khosravi, H.; Viberg, O.; Kovanovic, V.; Ferguson, R. Generative AI and Learning Analytics. J. Learn. Anal. 2023, 10, 1–6. [Google Scholar] [CrossRef]
- Steele, J.L. To GPT or not GPT? Empowering our students to learn with AI. Computers and Education: Artificial Intelligence. Comput. Educ. Artif. Intell. 2023, 5, 100160. [Google Scholar] [CrossRef]
- Bewersdorff, A.; Seßler, K.; Baur, A.; Kasneci, E.; Nerdel, C. Assessing student errors in experimentation using artificial intelligence and large language models: A comparative study with human raters. Comput. Educ. Artif. Intell. 2023, 5, 100177. [Google Scholar] [CrossRef]
- Farhi, F.; Jeljeli, R.; Aburezeq, I.; Dweikat, F.F.; Al-shami, S.A.; Slamene, R. Analyzing the students’ views, concerns, and perceived ethics about chat GPT usage. Comput. Educ. Artif. Intell. 2023, 5, 100180. [Google Scholar] [CrossRef]
- Relmasira, S.C.; Lai, Y.C.; Donaldson, J.P. Fostering AI Literacy in Elementary Science, Technology, Engineering, Art, and Mathematics (STEAM) Education in the Age of Generative AI. Sustainability 2023, 15, 13595. [Google Scholar] [CrossRef]
- Bai, X.; Stede, M. A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring. Int. J. Artif. Intell. Educ. 2022, 33, 992–1030. [Google Scholar] [CrossRef]
- Su, J.; Yang, W. Unlocking the Power of ChatGPT: A Framework for Applying Generative AI in Education. ECNU Rev. Educ. 2023, 6, 355–366. [Google Scholar] [CrossRef]
- Jauhiainen, J.S.; Guerra, A.G. Generative AI and ChatGPT in School Children’s Education: Evidence from a School Lesson. Sustainability 2023, 15, 14025. [Google Scholar] [CrossRef]
- Eysenbach, G. The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education: A Conversation with ChatGPT and a Call for Papers. JMIR Med. Educ. 2023, 9, e46885. [Google Scholar] [CrossRef] [PubMed]
- Rahman, M.M.; Watanobe, Y. ChatGPT for Education and Research: Opportunities, Threats, and Strategies. Appl. Sci. 2023, 13, 5783. [Google Scholar] [CrossRef]
- Halaweh, M. ChatGPT in education: Strategies for responsible implementation. Contemp. Educ. Technol. 2023, 15, ep421. [Google Scholar] [CrossRef]
- Schulze Balhorn, L.; Weber, J.M.; Buijsman, S.; Hildebrandt, J.R.; Ziefle, M.; Schweidtmann, A.M. Empirical assessment of ChatGPT’s answering capabilities in natural science and engineering. Sci. Rep. 2024, 14, 4998. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Z.; Wen, L.; Jiang, Y.; Liu, Y. Evaluate Chat-GPT’s programming capability in Swift through real university exam questions. In Softw: Pract Exper; Wiley: Hoboken, NJ, USA, 2024; pp. 1–15. [Google Scholar] [CrossRef]
- Katz, D.M.; Bommarito, M.J.; Gao, S.; Arredondo, P. GPT-4 passes the bar exam. Philosophical Transactions of the Royal Society A: Mathematical. Phys. Eng. Sci. 2024, 382, 20230254. [Google Scholar] [CrossRef] [PubMed]
- Maitland, A.; Fowkes, R.; Maitland, S. Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework. BMJ Open 2024, 14, e080558. [Google Scholar] [CrossRef]
- Currie, G.; Singh, C.; Nelson, T.; Nabasenja, C.; Al-Hayek, Y.; Spuur, K. ChatGPT in medical imaging higher education. Radiography 2023, 29, 792–799. [Google Scholar] [CrossRef] [PubMed]
- Ali, R.; Tang, O.Y.; Connolly, I.D.; Zadnik Sullivan, P.L.; Shin, J.H.; Fridley, J.S.; Asaad, W.F.; Cielo, D.; Oyelese, A.A.; Doberstein, C.E.; et al. Performance of ChatGPT and GPT-4 on Neurosurgery Written Board Examinations. Neurosurgery 2023, 93, 1353–1365. [Google Scholar] [CrossRef]
- Kung, T.H.; Cheatham, M.; Medenilla, A.; Sillos, C.; De Leon, L.; Elepaño, C.; Madriaga, M.; Aggabao, R.; Diaz-Candido, G.; Maningo, J.; et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS Digit. Health 2023, 2, e0000198. [Google Scholar] [CrossRef]
- Gilson, A.; Safranek, C.W.; Huang, T.; Socrates, V.; Chi, L.; Taylor, R.A.; Chartash, D. How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Med. Educ. 2023, 9, e45312. [Google Scholar] [CrossRef]
- Antaki, F.; Touma, S.; Milad, D.; El-Khoury, J.; Duval, R. Evaluating the Performance of ChatGPT in Ophthalmology. Ophthalmol. Sci. 2023, 3, 100324. [Google Scholar] [CrossRef]
- Terwiesch, C. Would Chat GPT3 Get a Wharton MBA? A Prediction Based on Its Performance in the Operations Management Course. Mack Institute for Innovation Management at the Wharton School, University of Pennsylvania. 2023. Available online: https://mackinstitute.wharton.upenn.edu/wp-content/uploads/2023/01/Christian-Terwiesch-Chat-GTP.pdf (accessed on 2 December 2023).
- Eulerich, M.; Sanatizadeh, A.; Vakilzadeh, H.; Wood, D.A. Is it All Hype? ChatGPT’s Performance and Disruptive Potential in the Accounting and Auditing Industries. SSRN Electron. J. 2023. [CrossRef]
- Kumar, K. Geotechnical Parrot Tales (GPT): Harnessing Large Language Models in Geotechnical Engineering. J. Geotech. Geoenviron. Eng. 2024, 150, 02523001. [Google Scholar] [CrossRef]
- Rane, N.; Choudhary, S.; Rane, J. Contribution of ChatGPT and Similar Generative Artificial Intelligence in Geotechnical Engineering and Soil Mechanics. SSRN Electron. J. 2024. [Google Scholar] [CrossRef]
- Fatahi, B.; Khabbaz, H.; Xue, J.; Hadgraft, R. Generative AI as a Catalyst for Enhanced Learning Experience in Engineering Education. In Proceedings of the AAEE 2023 Griffith University, Gold Coast, QLD, Australia, 3–6 December 2023. [Google Scholar]
- Daniel, W.W.; Cross, C.L. Biostatistics: A Foundation for Analysis in the Health Sciences; John Wiley & Sons: Hoboken, NJ, USA, 2018. [Google Scholar]
- Lwanga, S.K.; Lemeshow, S. Sample Size Determination in Health Studies: A Practical Manual; World Health Organization: Geneva, Switzerland, 1991. [Google Scholar]
- Krathwohl, D.R. A Revision of Bloom’s Taxonomy: An Overview. Theory Pract. 2002, 41, 212–218. [Google Scholar] [CrossRef]
Chapter Code | Topic Description |
---|---|
C2 | Origin of Soil and Grain Size |
C3 | Weight–Volume Relationships |
C4 | Plasticity and Structure of Soil |
C5 | Classification of Soil |
C6 | Soil Compaction |
C7 | Permeability |
C8 | Seepage |
C9 | In Situ Stresses |
C10 | Stresses in a Soil Mass |
C11 | Compressibility of Soil |
C12 | Shear Strength of Soil |
C13 | Lateral Earth Pressure: At-Rest Rankine and Coulomb |
C14 | Lateral Earth Pressure: Curved Failure Surface |
C15 | Slope Stability |
C16 | Soil Bearing Capacity for Shallow Foundations |
C17 | Subsoil Exploration |
Bloom’s Level | Question and Answer Summary | |
---|---|---|
Remember | Question: What is the formula to calculate the degree of saturation (S) in soil mechanics? | |
Answer: The degree of saturation (S) in soil mechanics is calculated using the formula , where is the specific gravity, is the water content in fraction, and is the void ratio. | ||
Understand | Question: Explain why the maximum dry density or unit weight of soil is important in soil compaction and how it is related to the moisture content. | |
Answer: The maximum dry density or unit weight of soil is crucial in soil compaction as it represents the highest density a soil can be compacted to at a given moisture content. It’s important for ensuring stability and support in engineering projects. The relationship with moisture content is significant as it determines the optimal water content at which the soil achieves its maximum dry density, leading to effective compaction and strength. | ||
Apply | Question: Given principal stresses = 150 kPa and = 50 kPa in a soil sample, and a friction angle (ϕ) of 30 degrees, calculate the normal stress (σn) and shear stress (τ) on a plane at an angle θ of 45 degrees using the relevant formulas. | |
Answer: To calculate the normal stress () and shear stress (τ) on a plane at an angle θ of 45 degrees, we use the formulas: Substituting the given values: = 150 kPa, = 50 kPa The calculated normal stress () and shear stress () on the plane at an angle of 45 degrees are: -Normal stress () = 100 kPa -Shear stress () = 50 kPa | ||
Analyse | Question: Given data for different soil samples including specific gravity, dry unit weight, and water content, determine the void ratio, degree of saturation, and wet unit weight for each sample. | |
Answer: To determine the void ratio, degree of saturation, and wet unit weight for each soil sample, the following steps are taken: -Calculate the void ratio () using the formula -Calculate the degree of saturation () using -Calculate the wet unit weight () using Specific calculations would depend on the provided data for each soil sample. | ||
Evaluate | Question: Critically assess the applicability of Mohr-Coulomb Failure Theory in predicting shear failure in a clayey soil, considering its cohesion and angle of internal friction. | |
Answer: The Mohr-Coulomb Failure Theory is a widely used criterion for predicting shear failure in soils. For clayey soils, which typically have significant cohesion, this theory can be effective in predicting failure. However, the theory assumes linear increase of shear strength with normal stress, which may not always accurately represent the complex behaviour of clay, especially under varied moisture and loading conditions. Thus, while useful, the theory should be applied with consideration of its limitations and possibly supplemented with empirical data specific to the type of clay. | ||
Create | Question: Design a method to experimentally determine the maximum and minimum void ratios of a soil sample, and subsequently calculate its relative density. | |
Answer: To experimentally determine the maximum and minimum void ratios, the following method could be designed: -For the maximum void ratio () Place a known volume of loosely poured soil in a container and measure its mass. Calculate the void ratio using the soil’s specific gravity and the volume of the container. -For the minimum void ratio () Place the same volume of soil in a container and compact it to its maximum density (e.g., using a mechanical compactor), then measure its mass. Calculate the void ratio as before. -With and , calculate the relative density () using This experiment would provide a comprehensive understanding of the soil’s packing characteristics. |
Prompted Question and Answer: |
Question: Given principal stresses = 150 kPa and = 50 kPa in a soil sample and a friction angle () of 30 degrees, calculate the normal stress () and shear stress () on a plane at an angle θ of 45 degrees using the relevant formulas. Answer: To calculate the normal stress () and shear stress () on a plane at an angle θ of 45 degrees, we use the formulas: Substituting the given values: = 150 kPa, = 50 kPa. The calculated normal stress () and shear stress () on the plane at an angle of 45 degrees are: -Normal stress () = 120 kPa − Shear stress () = 60 kPa. Can you check if the solution is correct? |
GPT’s Evaluation and Response: |
The correct normal stress () and shear stress () on the plane at an angle of 45 degrees, calculated using the given values of and kPa, are:
|
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, L.; Tophel, A.; Hettiyadura, U.; Kodikara, J. An Investigation into the Utility of Large Language Models in Geotechnical Education and Problem Solving. Geotechnics 2024, 4, 470-498. https://doi.org/10.3390/geotechnics4020026
Chen L, Tophel A, Hettiyadura U, Kodikara J. An Investigation into the Utility of Large Language Models in Geotechnical Education and Problem Solving. Geotechnics. 2024; 4(2):470-498. https://doi.org/10.3390/geotechnics4020026
Chicago/Turabian StyleChen, Liuxin, Amir Tophel, Umidu Hettiyadura, and Jayantha Kodikara. 2024. "An Investigation into the Utility of Large Language Models in Geotechnical Education and Problem Solving" Geotechnics 4, no. 2: 470-498. https://doi.org/10.3390/geotechnics4020026
APA StyleChen, L., Tophel, A., Hettiyadura, U., & Kodikara, J. (2024). An Investigation into the Utility of Large Language Models in Geotechnical Education and Problem Solving. Geotechnics, 4(2), 470-498. https://doi.org/10.3390/geotechnics4020026