Technology – never a day passes without news of some new, and even fascinating, development that will enhance our lives in some way. And it is very easy to become cynical about all this hype – all too often it seems that the only entity that really benefits from the new widget is the large multinational that markets it.
But putting cynicism aside, there are some new technologies that really will enhance our ability to monitor and manage our increasingly endangered environment.
Let’s look at some of them.
Since the launch of the first satellite in 1957, space technology has evolved dramatically. Just as an example, satellites were once as big as a school bus and weighed 6 tonnes. Today, not only can they be reusable, but they can also be as small as 0.1 kg (called picosatellites). Along with these size changes, capability changes have been equally dramatic.
In the field of environmental monitoring, satellites are used for monitoring climate change, monitoring natural resources and infrastructure and similar large-scale needs. In the area of communications, they can also be used to transmit data collected from remote location monitoring equipment.
The major problem is that purchasing and launching a satellite can be expensive. Even though costs have been reduced drastically (what was something like $400 million is now about $1 million), the most common environmental needs cannot justify these costs.
As of January 2024, there are 8,377 active satellites in various earth orbits. The largest number of these (3,135) are used for communications. Interestingly, 80% of communications satellites have launch masses below 300 kg.
Unmanned Aerial Vehicles (UAVs), or drones, have actually been around for a very long time. In 1849 unmanned balloons were used to bomb Venice – not very successfully, but it remains the first use of a military UAV. The British used them in WW1 to photograph German lines. But the use of predator drones (most people’s image of a drone) didn’t start until 1996. Today, of course, they are consumer items used for everything from photography to purchase deliveries, pandemic alleviation and many more things.
In environmental monitoring, drones are already being used for things like asset inspection, mapping of site deposits, vegetation monitoring, tailings dam monitoring, and access to unstable and potentially hazardous areas. There are even heavy-lift drones which can be used to deliver objects in excess of 100 kg into dangerous and/or difficult to access zones. They have also found use in air quality monitoring applications.
Consumer drones range from about $30 to $150 – they are very useful for gaining experience as a pilot. Drones for film and cinematography start at about $3,000 and drones for industrial use can be around $10,000. So it really is a question of horses for courses.
AI and ML Technologies:
AI is artificial intelligence and ML is machine learning – and many of us tend to use the terms interchangeably. While this confusion is understandable, as the two are related, it is important to appreciate the differences.
AI is a broad field which refers to the use of technologies to build machines and computers that have an ability to mimic cognitive functions associated with human intelligence. Thus it is not a system in itself, but a set of technologies implemented in a system to enable it to “reason, learn and act” to solve complex problems.
ML is a subset of AI that automatically enables a machine or system to learn and improve from experience. ML uses algorithms, rather than explicit programming, to analyse large amounts of data, learn from the insights and then make informed decisions. In other words, ML is an application of AI that allows machines to extract knowledge from data and learn form it autonomously. ML algorithms improve performance over time as they are “trained” – i.e. exposed to more data. The more data used, the better the model will become.
Like the other new technologies discussed here, the basics have been around for a long time.
In 1950, Alan Turing published “Computing Machinery and Intelligence”, introducing the Turing test and opening the door to what we now call AI. 1966 saw the creation of “Eliza”, a computer capable of engaging in conversations with humans. However, 1987 saw the arrival of the “AI winter” as even the introduction of the cheap personal computer still failed to transform AI into something useful.
Then the introduction of the current vast computing power gave rise to the era of Big Data. Machines can now trawl through vast amounts of data and identify patterns that no human could previously identify.
Currently Texcel is developing ML algorithms to interrogate its vast vibration, overpressure and noise databases to predict, for example, where and when levels are likely to exceed imposed limits.
We are also utilising AI to, for example, identify blast events from other vibration inducing events using recorded waveforms.
Introduction of these new technologies is Texcel’s way of ensuring our customers receive the best possible results from their projects.