“ At present around 8% of solid wastes generated all over the world are plastic wastes. 90% of plastic wastes end up in landfills. Without any treatment the plastic wastes take 500 years to 1000 years to decompose and release harmful chemicals while leaching. As per a World Bank 2016 report the world generated 242 MT of plastic wastes that was 12 % of all municipal solid wastes. East Asia and Pacific produced around 57 MT, Europe and Central Asia produced around 45 MT and North America produced around 35 MT.”

Plastic Waste Generation in India

According to a report released in the national capital, India produces approximately 3.4 million tons (MT) of plastic waste, with only 30 per cent of it being recycled. Over the span of five years, from the financial year 2016-17 to 2019-20, the country's plastic consumption has grown at a compounded annual growth rate (CAGR) of 9.7 per cent, increasing from 14 MT to 20 MT.
The report titled 'Plastics, The Potential and Possibilities' highlights that India's plastic waste output doubled during the mentioned period (Report by IISc and Praxis Global Alliance). The report further reveals that Maharashtra, Gujarat, and Tamil Nadu collectively account for 38 per cent of the total plastic waste generated in India.

Classification of Plastics

Plastics are mainly classified as follows:

• Polyethylene Terephthalate (PET)
• Polyethylene with a high density (HDPE)
• Polypropylene is a type of plastic (PP)
• Low-Density Polyethylene (LDPE)
• Others

Uses of Plastic

Plastics are used in several ways; Plastic products manufactured by industry include the following:

• Plastic bottles
• Plastic films
• Rigid plastics used in foam and fibers
• Others

Bio Degradable Plastics

Biodegradable plastic refers to a type of plastic material that can break down naturally in the environment through the action of microorganisms such as bacteria, fungi, and other living organisms. Unlike traditional plastics, which can persist in the environment for hundreds of years, biodegradable plastics are designed to degrade into simpler, non-toxic substances over time.

There are two main types of biodegradable plastics:

It's important to note that the term "biodegradable" does not necessarily mean that the plastic will degrade quickly in any environment. The rate of degradation depends on various factors, including the type of plastic, the environmental conditions (temperature, humidity, presence of microorganisms), and the specific biodegradation mechanism.

Biodegradable plastics offer potential benefits for reducing plastic waste and its impact on the environment. When properly managed, they can be composted or biologically degraded, leading to a reduction in plastic pollution and a more sustainable waste management approach.

However, it's essential to handle biodegradable plastics responsibly and ensure they are disposed of in appropriate waste streams, such as industrial composting facilities, where they can break down efficiently. If biodegradable plastics end up in standard landfill or marine environments, they might not degrade as expected and can still contribute to environmental pollution.

As with any environmental solution, it's crucial to consider the overall life cycle and environmental impact of biodegradable plastics, including their production, use, and end-of-life management.

Plastic Decomposing Enzyme

One notable example is the enzyme discovered in 2016 called PETase (short for polyethylene terephthalatease). PETase is an enzyme that has the ability to break down polyethylene terephthalate (PET), a type of plastic commonly used in bottles and packaging.

PETase was discovered in bacteria, specifically in Ideonella sakaiensis, found in the soil near a PET bottle recycling plant in Japan. The enzyme can catalyze the hydrolysis of PET, breaking it down into its constituent monomers, ethylene glycol, and terephthalic acid. This discovery has significant implications for plastic waste management and recycling efforts, as it could potentially lead to more efficient ways of breaking down PET plastics and reducing environmental pollution.

Furthermore, scientists have also been working on optimizing and engineering these enzymes to improve their efficiency and expand their plastic-degrading capabilities. Such advancements hold promise in tackling the global plastic waste problem and moving towards a more sustainable future.

Machine Learning and Plastic Decomposition

Machine learning has the potential to play a significant role in plastic decomposition and waste management efforts. Here are some ways in which machine learning can be applied to address the plastic waste problem:

It's important to note that while machine learning can be a powerful tool in addressing plastic waste, it is not a standalone solution. Combining machine learning with other approaches such as policy changes, public awareness, and improved waste management practices can collectively lead to more effective and sustainable plastic waste reduction efforts.l

HLPL for Plastic Decomposition deploying Machine Learning

For machine learning in the context of plastic decomposition, Python is currently the most popular and widely used high-level programming language. Here are some reasons why Python is well-suited for this purpose:

While Python is the language of choice for most machine learning tasks, other programming languages like R, Java, and C++ can also be used, depending on specific project requirements and constraints. However, for the reasons mentioned above, Python remains the most preferred language for machine learning, including plastic decomposition-related research and applications.

General Approach Algorithm for plastic decomposition using machine learning

One common approach to predicting degradation rates involves using regression algorithms, as it is a typical problem of predicting a continuous value (the degradation rate) based on input features.

The effectiveness of the machine learning model heavily depends on the quality and size of the dataset, the choice of features, and the algorithm used. Also, plastic degradation is a complex process influenced by various factors, so the accuracy of predictions might have limitations.
It's essential to consult with domain experts and researchers in the field of plastic decomposition to get the most relevant features and insights for the model. Additionally new advancements in research and machine learning latest literature and repositories for the most cutting-edge approaches in plastic decomposition using machine learning should be continuously updated and integrated with the existing body of knowledge in the subject.

A Specific Algorithm in Machine Learning for Plastic decomposition

One specific machine learning algorithm commonly used for regression tasks like predicting plastic degradation rates is the Random Forest Regression algorithm. It can handle both numerical and categorical features, which makes it suitable for working with diverse datasets that include environmental conditions and plastic types.

Here's how you can use Random Forest Regression in Python for plastic decomposition:

Data Preparation: Gather and preprocess your dataset, ensuring it includes plastic samples with their degradation rates and relevant features such as temperature, humidity, pH level, plastic type, etc.

Data Split: Split your dataset into a training set and a testing set.

Import Libraries: Start by importing the necessary Python libraries.

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score

Load and Prepare Data: Load your dataset into a Pandas DataFrame and separate the target variable (degradation rate) from the input features.

# Load your dataset into a Pandas DataFrame (replace 'data.csv' with your dataset file)
data = pd.read_csv('data.csv')
# Separate the target variable (degradation rate) from the input features
X = data.drop('degradation_rate', axis=1)
y = data['degradation_rate']

Train-Test Split: Split the data into training and testing sets.

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

Initialize and Train the Model: Create an instance of the Random Forest Regression model, fit it to the training data, and make predictions on the testing data.

# Initialize the Random Forest Regression model
model = RandomForestRegressor(random_state=42)
# Fit the model to the training data
model.fit(X_train, y_train)
# Make predictions on the testing data
y_pred = model.predict(X_test)

Model Evaluation: Evaluate the model's performance using appropriate metrics like Mean Squared Error (MSE) and R-squared.

# Calculate Mean Squared Error (MSE)
mse = mean_squared_error(y_test, y_pred)

# Calculate R-squared (coefficient of determination)
r_squared = r2_score(y_test, y_pred)
# Print the evaluation metrics
print(f"Mean Squared Error: {mse}")
print(f"R-squared: {r_squared}")

Predict New Degradation Rates: Finally, you can use the trained model to predict degradation rates for new plastic samples by passing their corresponding feature values to the model.predict() function.

Please note that the above code is a basic example of using Random Forest Regression for plastic degradation prediction. For real-world applications, it's crucial to preprocess the data carefully, perform hyper-parameter tuning, and consider feature engineering and selection to improve model performance. Additionally, ensure that your dataset is diverse and representative of the problem you are trying to solve.

As research and advancements in the field of plastic decomposition using machine learning continue, other algorithms or approaches may emerge as more effective for specific scenarios. It's always a good idea to keep exploring the latest research and methodologies for the most up-to-date solutions.

Biodegradable Plastics and Machine Learning

Machine learning can be applied to various aspects of biodegradable plastic research and development, as well as its environmental impact. Here are some ways machine learning can be connected to biodegradable plastics:

By leveraging machine learning in these areas, researchers and industries can accelerate the development and adoption of biodegradable plastics, contributing to more sustainable practices and reduced environmental impact of plastic waste. As research in both biodegradable plastics and machine learning continues to evolve, the synergy between these fields is expected to play an essential role in addressing plastic pollution and promoting environmental sustainability.

Negative Impact of Plastic Wastes

The visibility of plastic waste has been increasingly evident due to its accumulation over the past decades, causing significant negative impacts on the environment and human health. Without any human intervention plastic wastes can take hundreds to thousands of years to decompose naturally depending upon the type (New Hampshire Department of Environmental Services). This prolonged persistence leads to various detrimental consequences. Major issues identified related to plastic wastes include man made floods due to clogging of drains, respiratory problems due to burning, and reduced animal lifespans when ingested. Moreover, when dumped into canals and oceans, it contaminates water bodies. In oceans, plastic accumulates in massive swirling gyres that stretch for miles, as reported by National Geographic. Under the sun's ultraviolet light, plastic undergoes degradation into "microplastics," which are incredibly difficult to recover, disrupting food chains and degrading natural habitats, as highlighted by the United States NOAA. Alarming projections from the Ellen MacArthur Foundation in 2016 suggest that, if no action is taken, the weight of plastic in the oceans may exceed that of fish by 2050.

Plastic Waste Management and Sustainability

Software Developers can make emerging technologies valuable for society by addressing sustainability issues like Plastic Wastes management. The World Economic Forum report predicts that in the next five years and among the top 10 fastest growing jobs, the profile of sustainability specialists will become the second fastest growing job after AI and machine learning specialists.

World’s Top 10 Recycling Companies:

Waste Management Incorporated, Canada RMD: 15455
Veolia Environmental Services, France, RMD: 12505
Republic Services Inc, Arizona, RMD: 10,299
Waste Connections Inc, Canada, RMD: 5389
Clean Harbours Inc., UK, RMD: 3412
GFL Environmental Inc, Canada, RMD: 3347
Stericycle Inc, Illinios, RMD 3309
Renewi PLC, UK, RMD 2415
Covanta Energy Corporation, USA, RMD 1870
Cleanway Waste Management Ltd., Australia, RMD 1819

India’s Top 10 Recycling Companies:

Let’s Recycle
Vermigold Ecotech
Attero
Synergy Waste Management Pvt. Ltd.
A2Z Group.
Eco-Wise Waste Management Pvt. Ltd.
Saahas Zero Waste
Antony Waste Handling Cell Pvt. Ltd.
UPL Environmental Engineers Ltd.
Sampurn(e)arth Environment Solutions Pvt. Ltd.