This dataset contains images of 7 waste materials, and the goal is to classify them into different categories. Here’s a brief description of each class:

Cardboard: Images of cardboard materials, such as packaging boxes, cartons, and paperboard. Compost: Images of organic waste that can be composted, including food scraps, plant matter, and biodegradable materials. Glass: Images of glass containers, bottles, and other glass waste. Metal: Images of metallic waste, such as aluminum cans, steel containers, and other metal objects. Paper: Images of paper waste, including newspapers, magazines, office paper, and cardboard. Plastic: Images of plastic materials, such as plastic bottles, bags, and containers. Trash: Images of miscellaneous waste that doesn’t fit into the other categories.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12145656%2F7096297ab054f505f4d788b86545ce5f%2F42979_2023_1706_Fig1_HTML.png?generation=1709547095589432&alt=media" alt=""> The dataset provides an opportunity to build a deep learning model that can automatically classify waste materials, contributing to better waste management and recycling efforts. You can explore the dataset, preprocess the images, and train a neural network to achieve accurate classification results.

Waste Classification (repackaged)

  Summary:

A repackaged version of the Kaggle “Waste Classification” dataset with a consistent multi-choice training schema and multiple splits.

  Splits:

cleaned: Only real-world photos that match the declared subclass (non-photos, PPT slides, icons, cartoons, or mismatches removed). Schema (columns):

image: Image file (datasets.Image). class: One of the four top-level categories. subclass: Fine-grained category (from folder… See the full description on the dataset page: https://huggingface.co/datasets/huaweilin/waste-classification.

🧠 Plastic Type Classification Dataset (3,000+ Images)

This dataset is designed for computer vision and image classification tasks aimed at identifying plastic types from real-world images. It serves as a foundational resource for projects in automated recycling, sustainability, and waste classification.

📌 Context & Purpose

Plastic pollution is a critical environmental issue. Identifying different plastic types using AI can greatly improve sorting, recycling, and awareness efforts.

This dataset was created: - To train image classification models that recognize various plastic types - To raise public awareness around common plastics and their recyclability - As a baseline for building AI-driven sustainability solutions

🔍 Data Collection

• Images sourced from:
  • Open image repositories like Unsplash
  • Web scraping tools such as BeautifulSoup4 and Selenium
• Keyword-based image retrieval for relevant plastic items
• Categorized manually into plastic type folders

⚠️ This dataset is uncleaned and unbalanced. You may need to preprocess it before use.

📂 Folder Structure

Each folder represents a plastic category: plastic_types/ ├── PET/ ├── PE/ ├── PC/ ├── PP/ ├── PS/ ├── Others/

🗃️ Categories & Visual Mapping

✅ PET (Polyethylene Terephthalate)

• Plastic Bottles (water, soda, juice, oil)
• Cosmetic Jars
• Transparent Food Containers
• Blister Packs (medicines)
• Thermoformed Trays / Ready-to-Eat Meals

✅ PE (Polyethylene - LDPE / HDPE)

• Plastic Shopping/Grocery Bags
• Milk Bottles, Detergent Bottles
• Garbage Cans
• Shrink Wrap / Agricultural Films
• Ice Cream Tubs

✅ PC (Polycarbonate)

• Baby Bottles, Sippy Cups
• Large Water Gallons
• Ketchup Containers
• Optical Discs (CDs/DVDs)
• Safety Goggles, Face Shields
• Automotive Plastics

✅ PP (Polypropylene)

• Takeaway Containers, Microwave Meal Trays
• Yogurt Cups, Disposable Tableware
• Straws
• Cosmetic Bottles (flip-top)
• Plastic Egg Cartons

✅ PS (Polystyrene)

• Foam Trays (fruits, meats)
• Disposable Cups/Plates
• Instant Noodle Cups
• Styrofoam Packaging
• CD/DVD Cases

✅ Others

PVC (Polyvinyl Chloride)

• Plumbing Pipes
• Transparent ID Covers
• Cling Film / Blister Packs (electronics)
• Faux Leather, Raincoats

ABS (Acrylonitrile Butadiene Styrene)

• LEGO and Plastic Toys
• Electronic Casings (keyboard, remotes, routers)
• Car Dashboard Panels
• Hard Shell Luggage

⚙️ Use Cases

• Image Classification (CNNs, Transfer Learning)
• Object Detection (YOLO, SSD)
• Dataset Cleaning, Balancing, and Augmentation
• AI for Sustainability & Recycling
• Education & Environmental Awareness Projects

📎 License

License: CC BY 4.0 (Attribution 4.0 International)
You are free to share and adapt with attribution.

🙌 Contribution

Feel free to suggest improvements, share cleaned versions, or contribute to annotation or labeling.

💡 Inspiration

Plastic waste is everywhere. This dataset hopes to spark innovation in using AI to identify and reduce plastic pollution — one image at a time 🌍✨

Here are a few use cases for this project:

1. Waste Management: The model can be used to automate waste sorting in recycling plants. By correctly identifying and separating different types of trash, recycling process optimization can be achieved, leading to more efficient and sustainable waste management practices.

2. Smart Cities: Municipalities could leverage this model in smart bins installed throughout the city. The bins would be able to identify what type of trash is being thrown away and flag when they're full of a certain type of material, helping to streamline trash collection and recycling.

3. Environmental Research: Researchers could leverage the model to analyze waste composition in different regions or communities. This could provide insights into consumption patterns and inform policy initiatives focused on waste reduction.

4. Consumer Education Apps: This model could power a consumer application designed to educate individuals about the proper way to dispose of trash. The application could identify the type of trash and offer advice on how to recycle or discard it properly.

5. Corporate Sustainability: Businesses could use this model to better manage and reduce their waste, contributing to their corporate social responsibility goals. For example, the model could help categorize and quantify the waste produced in corporate cafeterias, allowing for adjustments in sustainability practices.

Motivation

Waste. As we all know that waste has become commonplace in many countries in the world. There is nothing wrong, in terms of waste itself defined as the final product that can no longer be used (by humans); residue. The problem lies in 'how do we manage this waste, while we can't use it anymore?'. Several countries have issues related to waste because the rate of waste production is not comparable to its management efforts. These things can be a big problem for the ecosystem.

With this dataset. I hope we can help waste management efforts with computer vision technology. With this technology, we can identify, track, sort and process it accordingly.

Content

This dataset contains approximately 256K images (156K original data) representing two classes, Biodegradable and Non-biodegradable. - Biodegradable, contains materials which can be decomposed naturally by microorganisms, such as foods, plants, fruits, etc. The waste from this material can be processed into compost. - Non-biodegradable, contains materials that cannot be decomposed naturally, for example plastics, metals, inorganic elements, etc. The waste from this material will be recycled into new materials.

I add augmented data against imbalanced class. Augmented data made by manipulating original data. Image transformation used: horizontal flip, vertical flip, 90deg CW rotation, 90deg CCW rotation.

In this dataset, I divide the data into two subsets, training set and evaluation set. The training set itself was splitted into 4 parts due to some technical constraints (my internet bandwidth). The thing to know is that the part of the training set don't have a good data distribution. So, don't pass each part directly to your model. Concatenate each part to single dataset. See Quickstart.

Data files in this dataset have unique name to prevent them from overwritten theirself when concatenating. Below is filename reference. You will need this for filtering this dataset.

SUBSET.PART_CLASS_CATEGORY_ID.EXT

SUBSET, the subset where data belong in. Either TEST or TRAIN. PART, part number of subset. Only if the subset splitted into several parts. CLASS, the class of data. BIODEG for biodegradable, or NBIODEG for non-biodegradable. CATEGORY, category of data. ORI for original data, HFL for horizontal flip, VFL for vertical flip, CWR for clockwise rotation, CCW for counter clockwise rotation. ID, data identification number. EXT, data extension. Either .jpg or .jpeg.

Acknowledgements

In this part, i would like to give an attribution to several Kaggle's users because without their great work, this dataset would be incomplete. As i mentioned that this dataset's source consist of another Kaggle dataset. So, this is my responsibility to do this. - Food Images (Food-101) - (K Scott Mader) - Fruit and Vegetable Image Recognition - (Kritik Seth) - Waste Classification data - (Sashaank Sekar) - Waste Classification Data v2 - (sapal6) - waste_pictures - (且听风吟)

Here are a few use cases for this project:

1. Waste Sorting: This model could be used in waste management facilities to automate the process of sorting garbage into different classes, increasing the efficiency and accuracy of recycling efforts.

2. Public Cleanliness: The model could be integrated into smart city systems to monitor public spaces for litter, helping municipalities identify areas that need to be cleaned or require better waste management solutions.

3. Education and Raising Awareness: The model could be utilized in educational campaigns or apps aiming to raise public awareness about the kinds of waste they generate, how it can be properly disposed of or recycled, and understanding the environmental impact of different waste materials.

4. Business Sustainability: Companies, especially in the manufacturing and packaging industries, could use this model to audit their waste production and develop more sustainable business practices - identifying areas where reuse or recycling could be increased.

5. Marine Conservation: The model could be used to analyze images or video footage of oceans and rivers to detect and classify waste, aiding in both cleanup efforts and research into plastic pollution.

The project explores the development of an AI model using computer vision for precise household waste classification, targeting plastics, cardboard, glass, cans, and paper. The literature review underscores the environmental concern in Costa Rica and examines AI techniques in solid waste management for enhanced efficiency and accuracy.The methodology employs a mixed approach, combining quantitative and applied elements. A carefully selected dataset and augmentation techniques are used to develop a robust AI model. Evaluation occurs in real household environments with active user participation. Results indicate good performance in classifying with positive user acceptance.

Here are a few use cases for this project:

1. Waste Management Systems: The refuse classification model can be used to streamline sorting processes in waste management facilities by automatically classifying garbage types, resulting in more efficient recycling processes and reducing harmful garbage misplaced in general waste.

2. Intelligent Bins: For the development of smart garbage bins that can classify the type of waste thrown in. Such bins could provide user feedback, encouraging proper waste sorting, or sort the waste internally to streamline recycling and disposal processes.

3. Environmental Education: The model could be incorporated into interactive educational apps to help teach children and adults about different types of waste, proper disposal methods, and the importance of recycling to create more environmentally-aware societies.

4. Smart Cities Implementation: The model can be used in implementing smart cities where each waste bin would have an integrated system to classify and sort the garbage. It could help in designing better waste processing strategies, optimizing waste collections and promoting effective recycling habits among residents.

5. Industrial Usage: Industries producing varying degrees and types of waste could use this model to properly segregate their waste. This would ensure efficient disposal, recyclability where possible, and could even help industries adhere to environmental standards and regulations.

The TACO: Trash Annotations in Context is an open image dataset that focuses on waste in various real-world settings. It encompasses a collection of images depicting litter in diverse environments, ranging from tropical beaches to urban streets in places like London. The dataset is notable for its manual labeling and segmentation, providing a hierarchical taxonomy for object detection algorithms to train and evaluate their performance. It comprises 1,500 images that cover 60 distinct waste classes, including items like aluminum_foil, batterie, and aluminum_blister_pack.

This dataset (JDD) is part of a data set that describes land use constraints related to anthropogenic risks, including, for each constraint, the government services or communities to be consulted.

The initial target corresponds to those involved in the management of urban planning who wish to know these constraints in a given area of the Greater East region. The accuracy corresponds to the municipality.

The current knowledge constraints induced by the storage of waste classified under ICPE correspond to the constraints associated with land use as a result of waste storage facilities under Classified Environment Facilities, which have not yet been the subject of a Public Utility Servitude Order. Restrictions on use are of the kind of risk of soil instability, potential accumulation of dangerous gases and groundwater pollution. A conservatory perimeter of 200 m around the facilities is to be considered. Since the associated constraints have not yet been brought to the attention of the mayors, DREAL would like to be consulted on projects potentially subject to constraints induced by these sites.

The objective of the layer is to identify the current knowledge constraints induced by the storage of waste classified under ICPE, to make available the information described above, and in particular to direct any consultations to the relevant interlocutors.

The data is intended for all persons who may consult the UDs and the SPRA on subjects related to anthropogenic risks, including the local authorities’ teaching services, the other departments of DREAL and the State, the notaries.

Contact point: The agent of the Anthropic Risk Prevention Service (SPRA) in charge of operational planning.

Name of the GIS layer: MU_DECHETS_EN_COURS_DREAL_R44.shp

This dataset contains images of various plastic objects commonly found in everyday life. Each image is annotated with bounding boxes around the plastic items, allowing for object detection tasks in computer vision applications. With a diverse range of items such as milk packets, ketchup pouches, pens, plastic bottles, polythene bags, shampoo bottles and pouches, chips packets, cleaning spray bottles, handwash bottles, and more, this dataset offers rich training material for developing object detection models.

This dataset is collected by DataCluster Labs, India. To download the full dataset or to submit a request for your new data collection needs, please drop a mail to: sales@datacluster.ai

The dataset is an extremely challenging set of over 4000+ original Plastic object images captured and crowdsourced from over 1000+ urban and rural areas, where each image is ** manually reviewed and verified** by computer vision professionals at Datacluster Labs.

Optimized for Generative AI, Visual Question Answering, Image Classification, and LMM development, this dataset provides a strong basis for achieving robust model performance.

Dataset Features

• Dataset size: 4000+
• Captured by: Over 1000+ crowdsource contributors
• Resolution: 99.9% images HD and above (1920x1080 and above)
• Location: Captured across 500+ cities
• Diversity: Various lighting conditions like day, night, varied distances, different material view points etc.
• Device used: Captured using mobile phones in 2020-2022
• Usage: Plastic object detection, Recycling and waste management, Garbage segregation, Trash segregation, etc.

Available Annotation formats

COCO, YOLO, PASCAL-VOC, Tf-Record

The images in this dataset are exclusively owned by Data Cluster Labs and were not downloaded from the internet. To access a larger portion of the training dataset for research and commercial purposes, a license can be purchased. Contact us at sales@datacluster.ai Visit www.datacluster.ai to know more.

The National Waste Management Database (upgraded) presents the spatial locations of Australia's known landfills, waste transfer stations and a large number of waste reprocessing facilities. The data are a compilation of Australian, jurisdictional government, council and industry databases.

The purpose of the National Waste Management Database is to support decision makers from industry, governments and other interested parties make better, and more informed decisions based on evidence based information.

The National Waste Management Site Database fields include:

NAME - Name of the feature. LANDFILL - Landfill classification (Closed, Not Applicable, Operating, Unknown) REPROCESSING - Recycling plant classification (Closed, Not Applicable, Operating, Unknown) TRANSFERSTATION - Transfer station classification (Closed, Not Applicable, Operating, Unknown) OPERATOR - Operator of the facility OWNER - Owner of facility SITEID - Geoscience Australia generated unique ID for feature SITEADDRESS - Street address of feature SITESUBURB - Suburb feature located in POSTCODE - Postcode for feature STATE - State feature located in FEATURERELIABILITY - Reliability/currency date of FEATURESOURCE FEATURESOURCE - Image or file name used to validate/digitize feature ATTRIBUTERELIABILITY - Reliability/currency date of ATTRIBUTESOURCE ATTRIBUTESOURCE - Authority, Organisation sourced for validating feature PLANIMETRICACCURACY - Planimetric accuracy of image used to digitize the feature SPATIALCONFIDENCE - 1 to 5 (1 bad - 5 excellent) rating of spatial and attribute data METADATACOMMENT - Comment field

Geoscience Australia compiled this database with the assistance of the following:

• Local governments / councils

• Australian Capital Territory Government - ACT No Waste

• New South Wales State Government - Department of Environment, Climate Change and Water

• Northern Territory Government - Natural Resources, Environment, the Arts & Sport

• Queensland State Government - Natural Resources and Environment

• South Australian State Government - Environment Protection Authority

• Victorian State Government - Environment Strategies Unit

• Western Australian State Government - Department of Environment and Conservation

• Waste Management Association of Australia

• Department of the Environment and Energy

• Veolia Environment

• Geoscience Australia - National Geographic Information GroupCC - Attribution (CC BY) This material is released by Geoscience Australia under the Creative Commons Attribution 3.0 Australia Licence. This material is released by Geoscience Australia under the Creative Commons Attribution 3.0 Australia Licence.

Here are a few use cases for this project:

1. Waste Management and Sorting: This model can be used in waste management systems to automatically sort and classify garbage according to its type. It can be particularly useful in recycling plants where precise categorization of different trash classes is necessary.

2. Public Health Monitoring: Municipalities can use this model to identify areas with high levels of unsanitized garbage. It can help track sanitation issues in cities and contribute to the optimization of waste collection routes.

3. Smart Bin Technology: This model can be integrated into IoT devices in smart bins, assisting in identifying the type of waste being thrown away. These bins can then provide feedback to users about appropriate disposal methods or inform waste collectors about the garbage content for better disposal strategies.

4. Marine Pollution Tracking: Used in combination with drone or satellite technology, this model could be used to detect and categorize garbage polluting oceans and seas. It can help in prioritizing and strategizing clean-up efforts.

5. Education and Awareness Campaigns: The model can help in creating interactive apps or platforms to promote waste segregation and recycling. Users can snap photos of their waste, and the model can inform them into which category their waste falls, promoting better waste disposal habits.

Abstract The Waste Management Facilities Database presents the spatial locations; in point format, all known waste management, recycling and reprocessing facilities within Australia. The Department of Agriculture, Water and Environment (DAWE) compiled this database with the following public and private agencies:

Geoscience Australia Qld Dept of Environment and Science Canberra Region Joint Organisation Hunter Joint Organisation of Councils NetWaste Illawarra Shoalhaven Joint Organisation ACT City Services NT council websites SA council websites Tas council websites Metropolitan Waste & Resource Recovery Group Loddon Mallee Waste & Resource Recovery Group Barwon South West Waste & Resource Recovery Group Grampians Central West Waste & Resource Recovery Group Gippsland Waste & Resource Recovery Group North East Waste & Resource Recovery Group Goulburn Valley Waste & Resource Recovery Group WA council websites Cleanaway website Veolia website Repurpose It website Advanced Circular Polymers website NSW Return and Earn Qld Containers for Change NT Container Deposits SA Container Deposit Locations ACT Container Deposit Locations NSW EPA SA EPA Re.Group website Bingo Industries website Industry sources Coles website Woolworths website ACT Government EPA Tasmania WA DWER National TV and computer drop-off locations Green Industries SA Qld Dept of Environment and Science AORA NSW EPA NT EPA APCO Qld council websites NSW council websites Vic council websites Sustainability Victoria Norske Skog Australia website InfraBuild website Liberty Primary Steel website Recycal website Sell and Parker website Future Recycling website TES-AMM Australia website Tambo Waste website NAWMA website Infrastructure survey responses WA DWER infrastructure survey responses

This database is for public, industry and government use under the CC-BY arrangements. Currency Date modified: 1 November 2022 Modification frequency: None Data extent Spatial extent North: -9.00° South: -44.00° East: 154.00° West: 112.00° Source information Catalog entry: Waste Management Facilities Database Lineage statement This dataset replaces the original first version of the data published on 1 January 2012; which did not include the recycling facilities. This updated version of the data contains the recycling facilities. The waste management facilities dataset underwent a complete update in 2022 using waste data captured by the Department of Agriculture, Water and Environment (DAWE). The dataset was address matched using the address provided with the Geocoded National Address File (G-NAF) data. Where no spatial location was provided, GIS specialists attempted to find a corresponding GNAF address and updates to this address were completed where possible. Visually located sites were found using Esri World Imagery and aligned to match a similar location on the block based on the surrounding GNAF address. For example center or front of block. Some locations were unable to be located due to lack of ground truthing capability. All other waste facilities contain the spatial and attribution originally received from DAWE. The imagery used ranges from one meter or better satellite and aerial sources. Data dictionary All layers

Attribute name Description

Object ID Automatically generated system ID

Shape Geometry type (Point)

Feature Type A single feature type “Waste Management Facility” is the collective name of the different facility subtypes identified in the CLASS field.

Unique Record ID Generate to define record uniquely.

GA_ID ID of waste management facility that originated from the original Geoscience dataset.

Unique Site ID The identification number used in the Geoscience Australia database.

Authority Name of Authority provided by the data custodian.

Licence No Licence number provided by the data custodian.

Co Located When a number of different activities are carried out at the same site

Facility Management Type The Management type subtypes: Recycling; Drop-Off; Disposal; Not Classified; Reuse; Energy From Waste

Facility Infrastructure Type The Infrastructure type subtypes: Metals Recovery Facility; E-Waste Drop-Off Facility; Container Deposit Scheme Dropoff Facility; Landfill – Putrescible; Other Waste Facility; Transfer Station; Other Recycling Facility; Plastics Reprocessing Facility; Organics Recycling Facility; E-Waste Recycling Facility; Paper and Cardboard Recycling Facility; C&D Waste Recycling Facility; Reuse Shop; Landfill – Not Classified; Steel Reprocessing Facility; Other Metals Reprocessing Facility; Plastics Recovery Facility; Materials Recovery Facility (MRF); Thermal Energy from Waste Facility; Landfill – Inert; Refuse Derived Fuel Facility; Mechanical Biological Treatment Facility; Glass Beneficiation Facility; Rubber Recycling Facility; Anaerobic Digestion Facility; Glass Reprocessing Facility; Mattress Recycling Facility

Facility Owner Owner of the facility.

Facility Name Name of the facility.

State The state where this feature is located.

Address The address of this feature.

Suburb The suburb where this feature is located.

Postcode The postcode where this feature is located.

Operational Status Operational; or Closed

Spatial Confidence 5 – High; 4 – Above Average; 3 – Average; 2 – Below Average; 1 – Low; 0 – None

Capture Method The method used to capture the spatial component of the data: G-NAF Address Match; Manually Located – G-NAF Match; Manually Located – No G-NAF Match; Spatial as Received – No G-NAF Match; Non Spatial; Retired Spatial Data

Address Detail PID - G-NAF The unique ID defined within the G-NAF address data.

Formatted Address - G-NAF The G-NAF address where this feature is located.

Suburb - G-NAF The G-NAF suburb where this feature is located.

Postcode - G-NAF The G-NAF postcode where this feature is located.

Confidence - G-NAF 2 - This reflects that all three contributors have supplied an identical address; 1 - This reflects that a match has been achieved between only two contributors; 0 - This reflects that a single contributor holds this address and no match has been achieved with either or the other two contributors; -1 - Was not used in this process.

Date Created - G-NAF G-NAF date of creation.

Date Last Modified - G-NAF G-NAF last modified date.

Date Retired - G-NAF G-NAF retired date.

Contact Geoscience Australia, clientservices@ga.gov.au

The Waste Management Facilities Database presents the spatial locations of Australia's known landfills, waste transfer stations and a large number of waste reprocessing facilities. The data are a …Show full descriptionThe Waste Management Facilities Database presents the spatial locations of Australia's known landfills, waste transfer stations and a large number of waste reprocessing facilities. The data are a compilation of Australian, jurisdictional government, council and industry databases. The purpose of the Waste Management Facilities Database is to support decision makers from industry, governments and other interested parties make better, and more informed decisions based on evidence based information. The Waste Management Facilities Database fields include: NAME - Name of the feature. LANDFILL - Landfill classification (Closed, Not Applicable, Operating, Unknown) REPROCESSING - Recycling plant classification (Closed, Not Applicable, Operating, Unknown) TRANSFERSTATION - Transfer station classification (Closed, Not Applicable, Operating, Unknown) OPERATOR - Operator of the facility OWNER - Owner of facility SITEID - Geoscience Australia generated unique ID for feature SITEADDRESS - Street address of feature SITESUBURB - Suburb feature located in POSTCODE - Postcode for feature STATE - State feature located in FEATURERELIABILITY - Reliability/currency date of FEATURESOURCE FEATURESOURCE - Image or file name used to validate/digitize feature ATTRIBUTERELIABILITY - Reliability/currency date of ATTRIBUTESOURCE ATTRIBUTESOURCE - Authority, Organisation sourced for validating feature PLANIMETRICACCURACY - Planimetric accuracy of image used to digitize the feature SPATIALCONFIDENCE - 1 to 5 (1 bad - 5 excellent) rating of spatial and attribute data METADATACOMMENT - Comment field Geoscience Australia compiled this database with the assistance of the following: - Local governments / councils - Australian Capital Territory Government - ACT No Waste - New South Wales State Government - Department of Environment, Climate Change and Water - Northern Territory Government - Natural Resources, Environment, the Arts & Sport - Queensland State Government - Natural Resources and Environment - South Australian State Government - Environment Protection Authority - Victorian State Government - Environment Strategies Unit - Western Australian State Government - Department of Environment and Conservation - Waste Management Association of Australia - Department of Sustainability, Environment, Water, Population and Communities - Veolia Environment - Geoscience Australia - National Geographic Information Group Note 1: This database is for public, industry and government use under the CC-BY arrangements. Note 2: A restricted version of this database is available to the list of data providers listed in the abstract. This database contains unique attribute linkages to specific industry and government aspatial databases.

This dataset (JDD) is part of a data set that describes land use constraints related to anthropogenic risks, including, for each constraint, the government services or communities to be consulted. The initial target corresponds to those involved in the management of urban planning who wish to know these constraints in a given area of the Greater East region. The accuracy corresponds to the municipality. Known constraints induced by storage of waste classified under ICPE correspond to the constraints associated with land use due to waste storage facilities under the Environmental Classified Facilities that have been the subject of a Public Utility Servitude Order. Easement clarifies the use restrictions (risk of soil instability, potential accumulation of hazardous gases and groundwater pollution) and the associated perimeter. This information has been brought to the attention of the mayors. DREAL does not need to be consulted on the constraints induced by these sites. The objective of the layer is to identify the known constraints induced by the storage of waste classified under ICPE, to make available the information described above, and in particular to direct any consultations to the relevant interlocutors. The data is intended for all persons who may consult the UDs and the SPRA on subjects related to anthropogenic risks, including the local authorities’ teaching services, the other departments of DREAL and the State, the notaries. Contact point: The agent of the Anthropic Risk Prevention Service (SPRA) in charge of operational planning. Name of the GIS layer: MU_DECHETS_CONNU_DREAL_R44.shp

A great challenge for waste-to-energy power plants is their uncertain and variable feedstock, which can lead to the power plants not being run as efficiently as possible, leading to reduced energy output and control of emissions. A way to describe the feedstock is to use surrogates. This is a method where the hundreds or thousands of different species of a feedstock are modelled using a few surrogate species, enabling the feedstock’s modelling. The surrogates also provide an estimation of the HHV and the fraction of biomass, oil-based waste and inorganics. This thesis formulated surrogates for waste classes typically incinerated, using a linear least-square solution between available surrogate species and experimental values. Most of the species used were from two existing models in the literature, but three new species were created to improve the representation of some waste classes containing fossil-originated wastes, rubber and PET. These were made by creating reactions based on experimental data from the literature and then testing these reactions under pyrolysis conditions in a stochastic reactor model. The surrogates for the waste classes were formulated by first dividing the waste into components and then finding the surrogate formulation for each component. There were found surrogates for 41 components, which were used to create the surrogate formulation for 30 waste classes. It was found that most of the surrogates modelled the elemental composition accurately compared to experimental values. A statistical overview of the experimental and model data for the waste classes was also created. This overview is relevant for stakeholders in waste management and for other research, such as life-cycle analysis.

Here are a few use cases for this project:

1. Smart Waste Sorting: The model may be used in a smart waste sorting system in residential complex or public areas, that can identify and segregate different types of waste based on their classes, thereby promoting organized waste management and recycling.

2. Recycling Plants: In recycling industries, the model can be used to sort different types of waste for optimized recycling processes. For instance, detection of paper, cardboard, aluminum, glass bottle, etc. could aid in their proper classification and processing.

3. Cleaning Robots: The model could be integrated into autonomous cleaning machines or robots to aid in household waste recognition and handling. It could help these machines to collect specific types of waste for disposal or recycling.

4. Environmental Advocacy: The application can also be useful for environmental groups and organizations, to demonstrate the types and amount of waste we generate daily. It could be used to raise awareness and promote more sustainable habits.

5. Waste Audit & Management: This computer vision model could be used by waste management companies or local authorities to conduct waste audits more efficiently, by swiftly categorizing the types of waste found in a specific location and helping to design better waste management strategies.

This dataset is a subset of the "WFD Classification Status Cycle 2" product. It contains summary data for the element ammonia for river water bodies, as used in the classification for Ecological status for the water framework directive (WFD). The ammonia classification dataset is an element of the physico-chemical group or element set and is used to consider particular phyisco-chemical conditions. Ammonia is hazardous due to its toxic and sub-lethal impacts on fish and macro-invertebrates. It is a decay product of nitrogenous organic wastes and of the breakdown of animal and vegetable wastes. Classifications are derived from spot sampling monitoring data, the results of which are calculated into percentiles and assessed against two different environmental quality standards (EQS), which are derived from site typology. Site classifications for ammonia use categories of High, Good, Moderate, Poor, and Bad. Attribution statement: © Environment Agency copyright and/or database right 2016. All rights reserved.

Today, the topic of waste separation has been raised for a long time, and some waste separation devices have been installed in large communities. However, the vast majority of domestic waste is still not properly sorted and put out, and the disposal of domestic waste still relies mostly on manual classification. The research in this paper applies deep learning to this persistent problem, which has important significance and impact. The domestic waste is classified into four categories: recyclable waste, kitchen waste, hazardous waste and other waste. The garbage classification model trained based on MobileNetV2 deep neural network can classify domestic garbage quickly and accurately, which can save a lot of labor, material and time costs. The absolute accuracy of the trained network model is 82.92%. In comparison with CNN network model, the classification accuracy of MobileNetV2 model is 15.42% higher than that of CNN model. In addition, the trained model is light enough to be better applied to mobile.