0% found this document useful (0 votes)
2 views20 pages

Supervised Vs Unsupervised Learning

The document explains the differences between supervised and unsupervised learning in the context of agriculture, highlighting how AI learns patterns from data to support farming decisions. Supervised learning involves providing examples with known outcomes for prediction, while unsupervised learning focuses on discovering patterns without labeled data. Both approaches are essential for effective decision-making in precision agriculture.

Uploaded by

manishraipr17
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views20 pages

Supervised Vs Unsupervised Learning

The document explains the differences between supervised and unsupervised learning in the context of agriculture, highlighting how AI learns patterns from data to support farming decisions. Supervised learning involves providing examples with known outcomes for prediction, while unsupervised learning focuses on discovering patterns without labeled data. Both approaches are essential for effective decision-making in precision agriculture.

Uploaded by

manishraipr17
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Supervised vs Unsupervised Learning

Two Ways AI Learns, Just Like


Farmers Do
Understanding how AI learns patterns from agricultural data to support smarter farming decisions.
FOUNDATION

Why This Topic Matters in Agriculture


The Critical Question The Stakes
Do I already know the correct answers? Or do I want AI to Choosing the wrong learning type leads to incorrect
discover patterns? recommendations and poor farm outcomes.
The Farming Connection
AI learns the way farmers learn—through experience and observation.

Farming Practice ML Learning Type Approach

Teaching a worker crop vs weed Supervised With examples

Observing field patterns Unsupervised Discovery

Yield prediction Supervised With history

Soil type grouping Unsupervised Pattern finding


What is Machine Learning?

Simple Definition Two Broad Ways


Learning patterns from past farm data to support future With known answers
decisions. Without known answers
SUPERVISED

Supervised Learning
01 02 03

Provide Input + Correct Answer AI Learns the Relationship Make Predictions


You give the AI examples with known The system identifies patterns connecting AI applies learned patterns to new, unseen
outcomes. inputs to outputs. data.

Like training a new farm worker with examples.


Supervised Learning: Farming Example
Training Phase Result

Farmer says: Worker can identify new plants correctly without guidance.

"This image = crop" The AI has learned to distinguish crops from weeds
"This image = weed" independently.

After many examples...


Supervised Learning Data Structure
Rainfall Soil Moisture Yield

200 mm 30% 3200 kg

180 mm 28% 3000 kg

220 mm 35% 3500 kg

Yield is the label (known answer) that guides the learning process.
Supervised Learning Demonstration
import numpy as np
from sklearn.linear_model import LinearRegression

# Training data: past seasons


rainfall = [Link]([[200], [180], [220], [210]])
yield_kg = [Link]([3200, 3000, 3500, 3400])

# Train supervised model


model = LinearRegression()
[Link](rainfall, yield_kg)

# Predict yield for new season


[Link]([[205]])
Code Explanation: Line by Line
rainfall → Input
1
Historical rainfall data (known values)

yield_kg → Label
2
Correct answer for each input

Model Learns
3
Identifies relationship between rainfall and yield

Prediction
4
Estimates yield for unseen rainfall amounts

This is learning with guidance.


When to Use Supervised Learning

Correct Answers Available Goal is Prediction


Historical data with known outcomes exists. You need to forecast or classify future events.

Agriculture Examples:

Yield prediction
Crop disease detection
Crop vs weed identification
UNSUPERVISED

Unsupervised Learning
Data Only AI Discovers Structure
You provide measurements without labels or correct The system finds patterns and groupings independently.
answers.

Like exploring a new field without instructions.


Unsupervised Learning: Farming Example

Group Similar Areas


Observe Patterns Identify zones with shared properties
Enter New Region Examine characteristics across —that's clustering.
Unknown soil types and crop patterns different areas.
await.
Unsupervised Learning Data Structure
Soil pH Moisture Nitrogen

6.5 30% High

7.2 45% Medium

6.8 35% High

No labels provided—only measurements for the AI to analyze.


Unsupervised Learning Demonstration
from [Link] import KMeans
import pandas as pd

# Soil data without labels


soil_data = [Link]({
"pH": [6.5, 6.8, 7.2, 7.5, 6.6],
"Moisture": [30, 35, 45, 50, 32]
})

# Group soil types automatically


kmeans = KMeans(n_clusters=2, random_state=0)
soil_data["Group"] = kmeans.fit_predict(soil_data)

soil_data
Code Explanation: Pattern Discovery
1 Measurements Only 2 Automatic Grouping 3 Pattern Discovery
Only soil pH and moisture AI groups similar soils without System reveals natural clusters in
provided—no type labels. human guidance. the data.
When to Use Unsupervised Learning

No Labeled Data Goal is Exploration


Correct answers don't exist or are unavailable. You want to discover patterns or group similar items.

Agriculture Examples:

Soil zone identification


Farm segmentation
Crop behavior grouping
Supervised vs Unsupervised: Comparison
Aspect Supervised Unsupervised

Labels Required Not required

Goal Predict outcomes Discover patterns

Example Yield forecast Soil clustering

Risk Label errors Interpretation challenges


Real Agriculture Case Study
Smart Advisory System

Unsupervised Phase Supervised Phase

Group farms by soil characteristics and climate patterns. Predict yield inside each discovered group.

Most real systems use both approaches together for optimal results.
Motivation for Non-Programmers

Not Learning Algorithms Why Data Matters How Systems Think


You're understanding how AI is Learn why data preparation is critical Understand advisory system logic to
trained and makes decisions. for AI success. trust or question outputs intelligently.
Key Takeaways
1 2

Supervised = Teaching with Examples Unsupervised = Discovering Patterns


Provide inputs and correct answers for AI to learn Let AI find structure in data without guidance.
relationships.

3 4

Labels Decide the Approach Both Are Essential


Available labels determine which learning method to use. Precision agriculture, AI advisory platforms, and sustainable
decision-making require both approaches.

Right learning type = Right harvest

You might also like