Will You Be a Digital Winner or a Digital Loser?

Every time waste is thrown into a waste bin, it ends up somewhere and has to be treated in some way so as not to be hazardous to the environment. The waste disposal process in many cities has transformed into a highly smart operation management activity. An IoT, ML-enabled platform for waste management adds a dimension of agile, real-time mapping and tracking that can improve waste management outcomes.

Waste disposal is a huge challenge for major cities. Today, government administrations in smart cities like Singapore, Dubai, Hong Kong, Amsterdam, Stockholm, Tokyo, Melbourne, Seattle, Chicago and Seoul have provided a massive push to incorporate technology into every aspect of their cities. The waste disposal process in many of these cities has transformed into a highly smart operation management activity.

Civic Waste Management

Today, civic waste management of any smart city is an interplay of on-field devices, or sensors, networked together to generate millions of data points; data thus obtained is then ingested into a cloud platform and fed through complex analytical frameworks to analyze and then to derive sensible, actionable inferences to better serve the citizens of that city. The whole process is automated with almost zero human interference.

Categorizing Waste

We all know waste can be placed under a few broad categories; paper waste, plastic waste, food product waste, water soluble waste, water insoluble waste, animal waste, sanitary waste, domestic waste, industrial waste and so on. Some of them are biodegradable and some aren’t; some could even be radioactive waste, which is highly toxic and potentially hazardous.

A Smart Solution

We developed an application that enables an alert when a conscious citizen on the road snaps a picture of waste lying on the road or of an overloaded, tipping-over-the-road waste bin and sends it to the command center using a cross-platform-compatible mobile app. The picture received by the command center can then be analyzed using an image point and vector framework analyzer to ascertain both the approximate quantities as well as the possible categories of the different waste materials captured in the image. The process flow requires no human intervention and it uses a smart algorithm to match with past and existing data. Nearly 90 percent accuracy has been achieved over time, specific to this activity.

IoT-driven Data Analysis and Machine Learning

The sensors attached to the roadside waste bins track waste collection inside the bin and alert the waste collection trucks automatically using an IoT-integrated and networked system, but waste that is thrown directly on the road escapes the digital visual eyes of the sensor cameras. It needs an alert and a conscious citizen or human interference to cover that piece of the waste thrown on the road by an errant citizen. The caveat here is that the alert and the conscious citizen must have basic knowledge of photography and must be comfortable using apps on smartphones.

Data from both the sensors and the pictures sent by an alert and a conscious citizen are through a complex system of multi-point and multi-layered analytics. We use past waste data to train the system on a machine learning (ML) platform to identify and categorize waste and also approximately to gauge the weight of the waste. The ML platform uses past images of waste taken from over 60 bin locations in the city, at various hours of the day. The ML platform is also trained on regular items generally found in and around waste bins so it can identify them easily.

Last Mile Capacity Management to Dispose of Waste

Every time waste is thrown into a waste bin, it ends up somewhere and has to be treated in some way so as not to be hazardous to the environment or to the citizens of the city. Therefore, it’s of utmost importance to ensure waste is treated appropriately. In order to treat waste appropriately, there is an absolute need to first ascertain what kind of waste it is.

Capacity Management for Disposal

Typical strategies adopted to dispose waste include recycling, volume reduction or conversion to energy and dumping into landfills or putting it through incinerators before dumping non-incinerable waste into landfills.

Using our application and back-end ML analysis, the incineration centers and landfills can do capacity management every hour with a dashboard to track each activity and to map daily output and landfill usage. That enables them to do accurate sizing by smart usage of combustion processes, quantity of flue gas to be used as well as knowing the electricity needed.

The quantity of collected byproducts of flue gas, ash generated, and solid lumps of inorganic constituents that aren’t burnt are also mapped. Suitable actions can be activated in collaboration with the other government authorities of the city, well before the waste reaches the incineration centers.

Pyrolysis, which is essentially the thermal decomposition of solid waste through the application of heat without the addition of extra air or oxygen, produces hydrogen, methane, carbon mono-oxide, tar oil and other inert materials as byproducts. The weight of these byproducts is also tracked to ensure these don’t pose major health and environmental hazards. The byproducts from the incineration centers include low-grade concrete, which is then sold for bricks and other construction and manufacturing blocks, adhering to the specifications laid down by the government authorities.

Capacity management and the eventual disposal process can be mapped well before time, starting right from the point of waste picture stage at the command center.

Value Adds to the Legacy Process Management

Historically, the term capacity management used to mean “management of various inventories in a manufacturing factory” or “right sizing of internal service delivery to meet current and future business goals and objectives.” It’s a kind of process management. In practical usage, a legacy system incorporates external factors like availability of products, market dynamism, demand forecasts and internal resource allocation.

However, an IoT-based ML platform for waste management adds a dimension of agile, real-time mapping and tracking through smart use of technology, networking, device or sensor management, and machine automation. Integration of all these needs very little human interference, with most of the activities being automated and monitored round the clock by a smart machine with the ability to analyze pictorial data and to do a bit of number crunching, when needed.