Agentic AI Climate Monitoring and Smart Environmental Decision System
Project Overview
This project combines ESP32, IoT sensors, AI decision-making, n8n automation, Telegram voice notifications, Google Sheets logging, and ThingSpeak cloud analytics.
System Architecture
Sensors
|
V
ESP32
|
WiFi
|
+-------------+
| ThingSpeak |
+-------------+
|
V
+-------------+
| n8n AI |
+-------------+
|
+------+------+
| |
V V
Google Telegram
Sheets Voice Alerts
Hardware Components
| Component | Quantity |
|---|---|
| ESP32 Dev Board | 1 |
| DHT22 Sensor | 1 |
| MQ135 Gas Sensor | 1 |
| LDR Sensor | 1 |
| Soil Moisture Sensor | 1 |
Circuit Connections
DHT22 VCC -> 3.3V GND -> GND DATA -> GPIO4 MQ135 AO -> GPIO34 LDR OUT -> GPIO35 Soil Moisture AO -> GPIO32
Flowchart
Start | Initialize ESP32 | Connect WiFi | Read Sensors | Send to ThingSpeak | Trigger n8n | AI Analysis | Google Sheets | Telegram Alert | Voice Notification | Repeat
ESP32 Source Code
#include <WiFi.h>
#include <HTTPClient.h>
#include "DHT.h"
#define DHTPIN 4
#define DHTTYPE DHT22
DHT dht(DHTPIN,DHTTYPE);
void setup()
{
Serial.begin(115200);
dht.begin();
}
void loop()
{
float temp=dht.readTemperature();
float hum=dht.readHumidity();
int air=analogRead(34);
int light=analogRead(35);
int soil=analogRead(32);
// Upload data
delay(30000);
}
ThingSpeak Integration
1. Create ThingSpeak Account
2. Create Channel
3. Add Fields
4. Copy API Key
5. Insert API Key in ESP32 Code
Google Sheets Integration
| Timestamp | Temperature | Humidity | Air Quality | Light | Soil Moisture | Status |
|---|
n8n Workflow
Webhook | Function | Google Sheets | AI Analysis | Telegram Alert | Voice Message
AI Decision Logic
Temperature > 40°C => Heat Alert Humidity < 25% => Dry Alert Air Quality > 2500 => Pollution Alert Soil Moisture < 800 => Irrigation Required
Power Consumption Prediction
Power = (Fan Hours × 75W) + (Pump Hours × 120W) + (Light Hours × 20W)
Telegram Voice Alerts
The AI Agent generates text alerts and converts them to speech using TTS services such as OpenAI TTS, Google TTS, or ElevenLabs. The generated MP3 file is automatically sent to Telegram.
Future Enhancements
- Machine Learning Forecasting
- Automatic Irrigation Control
- Smart Greenhouse Automation
- LoRaWAN Support
- Multi-language Voice Assistant
Deployment
Deploy n8n using Docker, AWS, Google Cloud, or Azure. ESP32 continuously streams sensor data to cloud services.
