SDG 6 - Use Case

What is the SDG 6 clean water and sanitation activity? 

By 2030, expand international cooperation and capacity-building support to developing countries in water- and sanitation-related activities and programmes, including water harvesting, desalination, water efficiency, wastewater treatment, recycling and reuse technologies.

What are the three pillars of sustainability?

The 3 pillars of sustainability: environmental, social and economic. Sustainability is an essential part of facing current and future global challenges, not only those related to the environment

 

What are GREEN skills?

Green skills include technical knowledge, expertise and abilities that enable the effective use of green technologies and processes in professional settings. They draw on a range of knowledge, values, and attitudes to facilitate environmentally sustainable decision-making at work and in life.

What is TDS in water?

What is TDS? – Definition, Explanation. The water TDS full form is Total Dissolved Solids, which is the total concentration of dissolved substances in water. TDS comprises organic matter and inorganic salts such as potassium, sodium, calcium, magnesium, and others.

Permissible Limits of TDS and pH in Water

Total Dissolved Solids (TDS):

• Permissible Limit for Drinking Water (BIS 10500:2012 - India):
• Acceptable: 500 mg/L
• Permissible (in absence of an alternative source): 2000 mg/L
• WHO Guidelines for Drinking Water:
• TDS levels below 600 mg/L are generally acceptable.
• Impact of TDS Levels:
• < 300 mg/L: Excellent.
• 300–600 mg/L: Good.
• 600–900 mg/L: Fair.
• 900–1200 mg/L: Poor.
• > 1200 mg/L: Unacceptable (requires treatment).

What is pH in water?

Pure water is neutral, with a pH of 7.0. When chemicals are mixed with water, the mixture can become some level of either acidic or alkaline. Vinegar and lemon juice are acidic substances, while laundry detergents and ammonia are alkaline.

pH Levels:

• Permissible Range for Drinking Water:
• 6.5 to 8.5 (as per BIS 10500:2012 and WHO standards).
• Impact of pH Levels:
• < 6.5: Water becomes acidic and corrosive.
• > 8.5: Water may taste bitter and form scales in pipes/appliances.

How to Measure Water Quality

1. Key Water Quality Parameters:
• Physical Parameters:
• Temperature
• Turbidity
• Chemical Parameters:
• TDS, pH, hardness, alkalinity, nitrates, chlorides.
• Biological Parameters:
• Presence of bacteria (e.g., E. coli).
2. Methods to Measure Water Quality:
• Portable Water Testing Kits:
• Available for testing TDS, pH, and other chemical parameters.
• Example: TDS meters, pH strips, and digital pH testers.
• Lab Testing:
• Comprehensive testing for chemical and biological contaminants.
• Digital Sensors:
• IoT-based water quality sensors for continuous monitoring.
• Smart Meters:
• Connected to apps for real-time data logging.

---

Tools for Measuring Specific Parameters

1. TDS Measurement:
• Use a TDS Meter:
• Calibrated digital device to measure TDS in mg/L or ppm.
• Submerge the probe in water for instant readings.
• Formula (if using conductivity): TDS (mg/L)=EC (µS/cm)×conversion factor (0.5–0.7).\text{TDS (mg/L)} = \text{EC (µS/cm)} \times \text{conversion factor (0.5–0.7)}.
2. pH Measurement:
• pH Strips:
• Dip a strip in water and compare its color with a chart.
• Digital pH Meter:
• Provides accurate and instant pH readings.
• Titration Method:
• Lab-based technique for precise pH measurement.
3. Advanced Tools:
• IoT-Based Water Quality Monitoring Systems:
• Measures multiple parameters (pH, TDS, turbidity, dissolved oxygen).
• Provides real-time data and alerts via mobile apps.
• UV-Vis Spectrophotometers:
• For detecting heavy metals and other contaminants

Measuring Water Quality in Real Life

1. Example for a Typical Indian Home:
• Use a TDS meter to check water quality from a tap or RO system.
• Monitor pH with a digital tester to ensure compliance with standards.
• Perform a lab test annually for comprehensive analysis.
2. Steps:
• Collect a water sample in a clean container.
• Test TDS and pH using meters.
• Record readings and compare with permissible limits.
• If parameters are outside acceptable limits, consider treatment options:
• High TDS: Install or maintain an RO system.
• Low pH: Add alkaline filters to balance acidity.

Would you like guidance on selecting testing equipment or improving water quality at home? Yes!

Predictive analytics solution for SDG 6 using sample data and Python code. The example will focus on predicting household water demand based on historical data, temperature, and household size.

________________________________________

Step 1: Sample Data

Here's an example dataset:

Day Household Size Avg Temperature (°C) Water Usage (Liters)

1 4 25 150

2 5 27 180

3 4 30 170

4 6 28 200

5 4 24 140

6 5 26 160

7 6 29 190

________________________________________

# Importing Libraries

import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestRegressor

from sklearn.metrics import mean_squared_error, r2_score

import matplotlib.pyplot as plt

import seaborn as sns

# Sample Data – Change according to your original data

data = {

    "Day": [1, 2, 3, 4, 5, 6, 7],

    "Household Size": [4, 5, 4, 6, 4, 5, 6],

    "Avg Temperature (°C)": [25, 27, 30, 28, 24, 26, 29],

    "Water Usage (Liters)": [150, 180, 170, 200, 140, 160, 190]

}

# Convert to DataFrame

df = pd.DataFrame(data)

# Features and Target

X = df[["Household Size", "Avg Temperature (°C)"]]

y = df["Water Usage (Liters)"]

# Split into Training and Testing Data

X_train, X_test, y_train, y_test =

        train_test_split(X, y, test_size=0.3, random_state=42)

# Train Random Forest Regressor

model = RandomForestRegressor(n_estimators=100, random_state=42)

model.fit(X_train, y_train)

# Make Predictions

y_pred = model.predict(X_test)

# Evaluate Model

mse = mean_squared_error(y_test, y_pred)

r2 = r2_score(y_test, y_pred)

print("Mean Squared Error:", mse)

print("R-squared:", r2)

# Predict for a new scenario

new_data = pd.DataFrame({"Household Size": [5], "Avg Temperature (°C)": [28]})

predicted_usage = model.predict(new_data)

print("Predicted Water Usage (Liters):", predicted_usage[0])

Step 3: Solutions and Insights

1. Evaluation Metrics:

o Mean Squared Error (MSE): Quantifies how close the predictions are to the actual values.

o R-squared (R²): Indicates how well the features explain the variability of the target variable.

Mean Squared Error: 22.136666666666674

R-squared: 0.8576928571428571

2. Prediction for New Scenario:

o For a household size of 5 and average temperature of 28°C, the predicted water usage might be around 170 liters/day.

Predicted Water Usage (Liters): 180.4

3. Actionable Insights:

o Adjust Usage Patterns: Based on temperature and household size, suggest peak usage reduction.

o Efficient Planning: Water supply can be scheduled to match demand during high-usage periods.

Step 4: Visualization (Optional)

You can use libraries like Matplotlib or Seaborn to visualize the relationship between water usage and features.

# Visualize Data

sns.scatterplot(data=df, x="Avg Temperature (°C)", y="Water Usage (Liters)", hue="Household Size")

plt.title("Water Usage vs. Temperature and Household Size")

plt.show()

Plot

This example demonstrates how predictive analytics can be applied to household water management. Would you like help tailoring this solution for larger datasets or integrating it with external tools (like IoT sensors)?