Water and Artificial Intelligence
Looking out on a very still lake in Switzerland made me think about writing on a specific topic. On average, the body of an adult human being is 60% water, most of which is contained in the cells, which need water to live. As such in a manner of speaking we are made of water.
In rivers, the water that you touch is the last of what has passed and the first of that which comes; so with present time.
Leonardo da Vinci, XIX Philosophical Maxims. Morals. Polemics and Speculations, 1174.
In the same section Leonardo claims: necessity is the mistress and guide of nature. This analogy refers to the moment like water flowing; as if the water was a series of events and life was fluid not fixed.
We need water to survive, and it even has religious importance to many, it is such an ordinary yet significant part of our lives.
You may have heard whispers or discussions of water wars. Water will be a key cause for future conflict, there is no doubt. There may very well be irregularities in supply and demand, fresh water shortage and groundwater shrinkage. This information seems to flow continuously, like the water rushing past your hand. Less than one percent of earth surface water is suitable for human consumption, it becomes crucial that we save water so that our future generations survive. 70% of the world’s population suffer at least one month of water scarcity a year.
The Water Crisis So Far
- A report suggests that the US alone wastes 7 billion gallons of drinking water per day. An average U.S. citizen uses 100 gallons (375 liters) per day.
- In January 2018, when officials in Cape Town announced that the city of 4 million people was three months away from running out of municipal water, the world was stunned. Labelled “Day Zero” by local officials and brought on by three consecutive years of anemic rainfall, April 12, 2018, was to be the date of the largest drought-induced municipal water failure in modern history.
- Brazil’s São Paulo, a megacity of 20 million, faced its own Day Zero in 2015. The city turned off its water supply for 12 hours a day, forcing many businesses and industries to shut down.
- Fourteen of the world’s 20 megacities are now experiencing water scarcity or drought conditions.
- Disaster data compiled by the U.N. clearly shows floods are also getting worse. They are happening more frequently, especially in coastal regions and river valleys, and affecting more people. Of all major disasters in the world between 1995 and 2015, 90 percent were weather-related events, such as floods, storms, heatwaves, and droughts.
So how can Artificial Intelligence Contribute?
As mentioned in my previous articles: (1) AI should be used to reduce inequalities; (2) we have to be aware of the energy consumption when AI is used; (3) the risk to the crisis due to escalating digital insecurities.
Proceeding from that I do still believe that working within the filed of artificial intelligence can provide some benefits to contributing to solving some of the problems flowing towards us as a consequence of increased population, congregation and our changing climate.
Measuring and controlling to predict (smart water management). Artificial Neural Networks and Support Vector Machine (SVM) are being popularly used as they are less cost-effective when compared to big data mechanisms.
Analytics India has made a list of cases related to this that I will do my best to sum up:
- Greece, used the precipitation, temperature and groundwater level data as the vector for neural networks for prediction.
- US, Illinois has used the feedforward training algorithm for the prediction of pesticide quotation in groundwater. Texas. An observation was to forecast the groundwater level. The Sevier River Basin Utah, has developed an SVM model to forecast the streamflow of 6 months ahead using local climatological data with different time variations and previous stream volume flow.
- Northern France, applied the ANN model to estimate the depth of the contaminated territory in the soil to estimate groundwater contamination.
- Turkey, in the Harran Plain researchers used temperature, electrical conductivity, and Ph levels of groundwater as vectors for ANN.
- Iran ANN multilayer perceptron (MLP) to model the rainfall-runoff process using rainfall durations, average intensities and season index of over 100 occurrences as vectors for the model.
- Singapore has developed ANN for prediction of coastal water quality using the location of stations, previous salinity, temperature, dissolved oxygen levels and chlorophyll-a levels in the nearby stations as vectors.
- China used an SVM model for groundwater quality assessment at the Naingziguan fountain by using groundwater quality classification indicators as vectors, which resulted in high prediction accuracy.
- Korea used SVMs and ANNs to forecast groundwater level in wells near coastal regions. They used previous data of groundwater level, tide level and precipitation as vectors.
Let’s extend da Vinci’s analogy: Unless you have a very big hand, you can’t touch all the water passing a given point in a river. With big data however, we can touch more, yet not all. We must be wary of making predictions in fast changing world, yet we must as well attempt our best to use technological know-how responsibly with both social and environmental concerns in mind.
This is day 19 of #500daysofAI, I hope you enjoyed it.
What is #500daysofAI?
I am challenging myself to write and think about the topic of artificial intelligence for the next 500 days with the #500daysofAI. It is a challenge I invented to keep myself thinking of this topic and share my thoughts.
This is inspired by the film 500 Days of Summer where the main character tries to figure out where a love affair went sour, and in doing so, rediscovers his true passions in life.