Lesson Plans · Agriculture, Food & Natural Resources · Course 8073
Human + AI: Precision Agriculture and the Human Leader
An AI system analyzing drone imagery and soil sensors recommends doubling fertilizer on Field 7 — but the farmer walked that field yesterday and the soil felt wrong. Students interrogate the data like scientists, check the AI against the field, and sign the decision as the accountable humans.
New here? Watch this first — how an interactive lesson works (30 seconds).
VDOE Standards of Learning addressed
| Code | Standard |
|---|---|
| BIO.1 | Science — Biology (2018): Scientific and engineering practices — ask questions and define problems; plan and carry out investigations; interpret, analyze, and evaluate data; construct and critique conclusions from evidence; develop and use models. Students interrogate sensor data the way scientists interrogate lab data. |
| 9.R.1 | English 9 (2024): Evaluation and synthesis of information — evaluate sources for credibility and bias, synthesize, cite sources, and demonstrate ethical and responsible use of all sources including Artificial Intelligence (AI). |
| 9.C.1 / 9.C.2 | English 9 (2024): Collaborative discussion and presentation of ideas. |
| 9.W.1 / 9.W.2 | English 9 (2024): Expository writing — thesis, evidence from multiple authoritative sources, concluding section. |
| EPF.1 | Economics & Personal Finance (2019): Cost-benefit analysis and the PACED decision-making grid. Students weigh fertilizer cost and yield gain against runoff risk. |
CTE competencies — Applied Agricultural Concepts (course 8073)
| Strand | Competency area (Virginia CTE Resource Center) |
|---|---|
| 8073 | Soil, soil fertility, and cultural practices. |
| 8073 | Plant systems and disease/pest management. |
| 8073 | Food production, handling, and preparation. |
Workplace Readiness Skills
National Standards Alignment
| Framework | Alignment |
|---|---|
| Career Cluster | Agriculture, Food & Natural Resources (National Career Clusters Framework, Advance CTE) — the Field 7 fertilizer decision sits inside this national cluster. |
| Career Ready Practices | CRP-8 Utilize critical thinking to make sense of problems and persevere in solving them — interrogate sensor data like lab data; CRP-5 Consider the environmental, social and economic impacts of decisions — yield gain vs. cost vs. runoff; CRP-7 Employ valid and reliable research strategies — check AI claims against references and field notes |
| AI4K12 Big Ideas | Perception — soil sensors and drone imagery feed the AI analysis; Societal Impact — fertilizer runoff, watershed health, and the food supply |
National framework names verified September 25, 2026 against the Advance CTE National Career Clusters Framework, the Common Career Technical Core Career Ready Practices, and the AI4K12 Five Big Ideas (AAAI/CSTA). Advance CTE modernized the cluster framework in 2024; this lesson uses the classic cluster names shown on this site’s career-cluster pages. No codes were invented.
Learning objectives
By the end of this lesson, students will be able to:
- Explain how precision-agriculture tools — soil sensors, drone imagery, AI analysis — support farm decisions, and where each tool's limits lie. (8073: soil & plant systems)
- Plan and carry out a data investigation: interpret sensor readings, identify sources of error, and construct conclusions from evidence. (BIO.1)
- Apply “Direct it. Check it. Question it. Decide.” when using AI to analyze field data, and name the human accountable for the final recommendation. (9.R.1 · WRS-2 · WRS-15)
- Complete a PACED cost-benefit grid on the fertilizer recommendation, weighing yield gain against cost and environmental risk. (EPF.1)
- Write an expository brief defending the decision with a thesis, cited evidence, and a conclusion. (9.W.1 / 9.W.2)
Materials & vocabulary
Student devices with AI access · Field 7 data pack — a teacher-provided classroom scenario (sensor readings, drone summary, AI recommendation, farmer's field notes) · PACED grid handout · exit-brief template.
Vocabulary: precision agriculture · soil fertility · cultural practices · sensor data · variable-rate application · runoff · integrated pest management · AI direction
Lesson sequence
1. Engage — The Field 7 dilemma (10 min)
The AI says double the fertilizer; the farmer's boots say something is off. Poll the class: trust the AI, or trust the farmer? Data without judgment is just numbers.
2. Explore — How precision agriculture works (15 min)
Direct instruction: soil sensors, drone imagery, variable-rate application — what each tool measures and what it cannot see. Soil fertility basics (8073). Introduce the four-level model: Human Initiates, AI Analysis, Human Review, Authorized Decision.
3. Explain & Elaborate — Investigate Field 7 (35 min)
Teams of 3–4 run the Human + AI cycle on the data pack: Direct an AI tool to analyze the sensor readings and drone summary. Check the AI's claims against soil-science references and the farmer's field notes (BIO.1, 9.R.1, WRS-15). Question sources of error — sensor calibration, training-data bias, what the AI can't see: drainage, compaction, yesterday's rain. Then Decide: complete a PACED grid (EPF.1) — follow the recommendation, modify it, or reject it — and sign it as the accountable humans.
4. Evaluate — The brief (20 min)
Individual expository brief (9.W.1 / 9.W.2): follow the AI's recommendation or not? Thesis, evidence from the data pack and at least one cited source, conclusion. Required line: “What the data showed, what the field showed, and why I trust one over the other.”
5. Close — The leader walks the field (10 min)
Teams report decisions (9.C.2). Reflection: AI processed the data — only a human could walk Field 7. Connect to WRS-11 and WRS-13: the tools will keep changing; the leader's judgment is the constant.
Human + AI integration — in every lesson
“Direct it. Check it. Question it. Decide.”
- Human Purpose — students set the goal: a healthy crop, a healthy budget, and a healthy watershed.
- Understand the Task · Match the AI · Assign & Instruct — students direct the AI with a precise assignment: analyze the readings, not make the call.
- Navigate & Direct · Evaluate — students check every AI claim against references and field notes; question error, bias, and blind spots.
- Decide · Guide & Improve · Exercise Accountability — the team makes the final call on the PACED grid and signs it. The human decides; the AI advises.
Assessment rubric
| Criterion | Full credit |
|---|---|
| Data investigation | Sensor data interpreted correctly; at least one source of error identified; conclusions built from evidence. (BIO.1) |
| AI direction | AI claims checked against references and field notes; at least one AI blind spot or error identified. (9.R.1 · WRS-15) |
| Decision quality | PACED grid completed; recommendation follows from yield, cost, and runoff evidence. (EPF.1 · WRS-2) |
| Written brief | Clear thesis, cited evidence, “data vs. field” line, concluding statement. (9.W.1 / 9.W.2) |
| Accountability | A named human signs the team's recommendation; every member contributes. (WRS-10) |
Differentiation
Support: sentence frames for the brief; pre-filled PACED grid with two criteria; vocabulary bank on the handout.
Extension: research variable-rate application technology and model how nitrogen runoff from over-fertilization affects a local watershed.
Standards source note: BIO.1 verified September 21, 2026 against the official VDOE 2018 Science Standards of Learning Curriculum Framework (Biology); Applied Agricultural Concepts (course 8073) areas of instruction from the Virginia CTE Resource Center; English, Economics & Personal Finance, and Workplace Readiness Skills codes verified September 20, 2026 against official VDOE publications. Nothing was invented. Field 7 is a classroom scenario written for this lesson.