MIL Africa Engine

Source: The Conversation – Africa – By Riona Indhur, Postdoctoral Research Fellow, Durban University of Technology

Microplastics are the crumbs of our plastic world, tiny pieces that come from bigger items breaking apart or from products like synthetic clothing and packaging. They’re now everywhere. Scientists estimate there are about 51 trillion of these particles floating in the world’s surface waters, and low levels have even been found in South African tap water.

That’s worrying because these particles can carry chemicals and bad bacteria, get eaten by fish and other wildlife, and may end up in our bodies.

We’re water scientists who are looking for ways to solve this problem. In a recent study, we tested a practical fix: two “magnetic cleaning powders” that can attach onto microplastics in water; the combined clumps can then be pulled out using a magnet. These materials are called magnetic nanocomposites (think: very fine powders with special surfaces).

The idea is simple: mix a small dose of powder into the water, let it attract and attach to microplastics, and then use a strong magnet to remove the powder-plastic clusters, leaving cleaner water behind.

Around the world, researchers have tried many different methods to capture microplastics, but our study is among the first to show that magnetic nanocomposites can work effectively not only under laboratory conditions but also in real-world samples, including municipal wastewater and drinking water.

This is the first study to use these specific nanomaterials for microplastic removal, proving both their high efficiency and their practical potential. Most existing filters struggle to catch the smallest plastics, the ones most harmful to health and the environment. The next step is to test these powders on a larger scale and develop simple, affordable systems that households and water treatment plants can use.

How well do the powders work?

In our research we found that the powders were able to remove up to 96% of small polyethylene and 92% of polystyrene particles from purified water. When we tried the same approach in both drinking water and water coming out of a municipal wastewater treatment plant, the results were just as strong. In drinking water the removal was about 94% and in treated wastewater the removal was up to 92%.

Another finding from this study is that the size of the plastic particles matters. The smaller the microplastic, the easier it is for the powders to attach to it, because tiny particles can reach more of the powder’s special “sticky” surface. We saw very good results for small plastics (hundreds of micrometres), but bigger particles (3-5 millimetres) were hardly removed at all. This is because they don’t mix with the powder as well and there’s less surface for the powder to attach onto.

In everyday terms, these magnetic powders are excellent for the small microplastics that are hardest to catch with normal filters.

Now for the big question: why do the powders attach to plastic? Think of it as being like tiny magnets. The powder and the plastics have special surfaces. The powder has parts that are sticky for plastics. This stickiness happens because of different kinds of forces. The plastic and powders have opposite charges which pull them together or allow them to stick together.

The key point is that the powders are engineered or specifically made to grab onto plastics so that microplastics naturally cling to them in water.

Once the powders attach onto the microplastics, we use a strong magnet (magnetic force: 250kg) to pull the powder–plastic clumps out of the water. The plastics are then separated from the powder by washing and filtration, dried, and weighed. This allows us to check how much plastic was removed. The separated powders are regenerated and reused, while the plastics are safely discarded, preventing them from re-entering the water.

We also looked at real-world questions: can you reuse the powders? And are they safe? The powders themselves are made from safe, lab-engineered materials: tiny sheets of carbon and boron nitride (a material also found in cosmetics and coatings) that are coated with magnetic iron nanoparticles. This makes them stable in water, and easy to pull out with a magnet after they’ve captured the microplastics.

After three rounds of use, the tested powders were effective in removing plastics up to 80%. That means you don’t need a new batch of powder every time, which is important for keeping costs down. Treating 1,000 litres of water with this method costs about US$41 (R763), making it competitive with many existing treatment options.

For safety, we tested the filtered powder (the “filtrate”) on plant growth. The results showed minimal to no toxicity, as three different plants were able to grow well in the presence of the filtrate. This is a strong sign that the method is environmentally friendly when used as intended.

What does this study mean for households and cities?

In the short term, magnetic powders could be built into small cartridges or filter units that attach to household or community water systems, helping remove microplastics before the water is used for drinking or cooking.

But the bigger picture is just as important. Microplastics are not only a South African problem but are also a global pollutant that crosses borders through rivers, oceans, and even the air we breathe. Low-cost, scalable solutions such as magnetic powders can make a real difference in resource-limited settings, where advanced filtration systems are too expensive or impractical.

Looking ahead, further work will focus on scaling up the method, testing it under more diverse water conditions, and designing simple, affordable devices that households or treatment plants can adopt.

In short: this specialised magnetic powder can tackle a tiny pollutant with big consequences. With sensible engineering and careful recovery, magnetic nanocomposites offer a promising, practical path to clean water while protecting the ecosystem from microplastic pollution.

– We tested if a specialised magnetic powder could remove microplastics from drinking water: the answer is yes
– https://theconversation.com/we-tested-if-a-specialised-magnetic-powder-could-remove-microplastics-from-drinking-water-the-answer-is-yes-264058

Source: The Conversation – Africa – By Namhla Thando Matshanda, Associate Professor, Department of Political Sciences, University of Pretoria

The formal launch of Ethiopia’s Grand Ethiopian Renaissance Dam in September 2025 made news across the world. There was pomp and ceremony as Africa’s largest hydroelectric dam was officially inaugurated after 14 years and US$5 billion worth of project work.

The project’s completion fulfils a national dream long in the making. It was formally initiated by the late Meles Zenawi, who served as president of Ethiopia from 1991 to 1995 and as prime minister from 1995 until his death in 2012. But the idea of a dam on the Ethiopian Nile dates back even further. As early as the 1950s, Emperor Haile Selassie recognised the potential of a dam for Ethiopia’s developmental needs.

This vision has occupied the Ethiopian national imagination since then. That is why Ethiopians celebrated the launch as a significant national achievement. Prime Minister Abiy Ahmed hailed the dam as a “shared opportunity” for the region, which stands to gain from surplus electricity exports. The dam’s opening was also celebrated with street processions across the country.

The completion of the dam is a major achievement. As a hydropower source, it is expected to deliver practical benefits such as electricity supply to a large number of Ethiopians. More than that, the dam is also being used to galvanise national pride and unity.

As a scholar of African politics with an interest in Ethiopia and the Horn of Africa, my work has focused on the challenges of constructing national unity and inclusion in Ethiopia.

It is not surprising that the government has seized this moment. National pride and unity have been low in Ethiopia in recent years.

The quest for national cohesion has occupied Ethiopian state builders stretching back from the imperial state up until the present period. Previous attempts proved to be largely symbolic, however, with limited transformative power.

The Grand Ethiopian Renaissance Dam risks falling into the same pattern. Its inauguration comes in the aftermath of a largely unresolved conflict in Tigray, and amid intense political fragmentation and ongoing civil wars in Ethiopia. When the war with Tigray ended, others erupted in different parts of the country, most notably in the Amhara and Oromo regions.

Elusive national unity

Ethiopia is a diverse country of over 120 million people. It comprises multiple ethnic, linguistic and religious groups.

Over 80 languages are spoken, with Amharic as the lingua franca. The largest ethnic groups correspond with the most widely spoken languages: Oromiffa, Amharic, Tigrinya and Somali.

Since the late 19th century, various leaders have attempted to construct a nation alongside the state. A state comes into being with the determination of borders and international recognition. Crafting a nation is different. It is the process of establishing a sense of common identity and purpose among the inhabitants of a state. The process of nation-making has been violently contested and fraught in Ethiopian political history.

The results of this contested history can show up in the most unlikely places. For instance, the grand opening of the dam was timed to fall in the month of Meskerem (September). It came a few days before the Ethiopian new year – Enkutatash – which is celebrated on 11 September. This holiday is a major event in the Ethiopian calendar and is usually marked by national celebrations.

However, the holiday is rooted in Ethiopian Orthodox traditions. It carries huge symbolism for at least one particular group – Ethiopia’s Orthodox Christians, who are just over 43% of the population. But others could have felt excluded by this choice.

This has not dissuaded those in power, throughout history, from using such symbolic events and occasions to foster a sense of national unity.

Symbolic nationalism

The imperial regime of Haile Selassie made concerted efforts to unite the nation following the Italian occupation of 1935. At this time, state sovereignty was compromised, with some sections of the country still under foreign occupation. The country was divided between those that resisted the occupation and those who collaborated with the Italians.

To build legitimacy and unity, the emperor turned to the heroic efforts of the patriotic resistance against the Italian occupation as a source of national pride. He also engaged in a policy of state modernisation. One of the key developments from this period was the establishment of Ethiopian Airlines in 1945.

The airline has been highly successful – and profitable. It has contributed to strengthening the Ethiopian brand. But it has not in any visible measure delivered long-term national unity and prevented political violence in Ethiopia.

The post-1991 government also made use of symbols and events to foster national unity. Amid growing concerns about where the ruling coalition was taking the country, in the lead up to the year 2007 (2000 according to the Ethiopian calendar), the government organised millennium celebrations. These captured the nation’s imagination and provided temporary respite from political tensions. Indeed, the initial name of the Grand Ethiopian Renaissance Dam was the Millennium Dam.

What these symbolic attempts managed to achieve is short-lived national pride. They also drew attention away from the structural challenges facing the country.

What is needed to achieve long-term national unity

Ethiopia must come to terms with the deep-seated issues of inequality, historical and contemporary grievances of exclusion and marginalisation. These are the key drivers of recurring cycles of political violence. The country needs to have honest conversations, in non-partisan platforms.

The National Dialogue that is currently underway is a good place to start. The process was launched in 2022 to address key national questions thrown up in part by the disastrous Tigray war. The dialogue seeks to create conducive conditions for national consensus on the root causes of divisions in the country.

National dialogues are useful tools that have been used in diverse national contexts for the purpose of conflict transformation and addressing internal conflicts. These have potential to yield positive results if they are inclusive and have clear implementation plans.

There are fears, however, that the dialogue might be undermined by the Ethiopian government, especially in light of elections in 2026. The government might use the national dialogue to advance its position and present itself in a positive light in relation to its political opponents.

If the National Dialogue fails to achieve its intended objectives, then it will be left to the different communities in Ethiopia to organise their own non-partisan platforms where they can have these urgent national conversations. Here, they would need to find consensus on key areas of national concern and collectively seek solutions. In so doing, Ethiopians would have taken significant steps towards nation building.

– Ethiopia has struggled to build national unity: can its big new dam deliver it?
– https://theconversation.com/ethiopia-has-struggled-to-build-national-unity-can-its-big-new-dam-deliver-it-265630

Source: The Conversation – Africa – By Laura Ferguson, Associate Professor, Population and Public Health Sciences, University of Southern California

Globally, nearly half of the deaths of children under five years are linked to malnutrition. In Kenya, it’s the leading cause of illness and death among children.

Children with malnutrition typically show signs of recent and severe weight loss. They may also have swollen ankles and feet. Acute malnutrition among children is usually the result of eating insufficient food or having infectious diseases, especially diarrhoea.

Acute malnutrition weakens a child’s immune system. This can lead to increased susceptibility to infectious diseases like pneumonia. It can also cause more severe illness and an increased risk of death.

Currently, the Kenyan national response to malnutrition, implemented by the ministry of health, is based on historical trends of malnutrition. This means that if cases of malnutrition have been reported in a certain month, the ministry anticipates a repeat during a similar month in subsequent years. Currently, no statistical modelling guides responses, which has limited their accuracy.

The health ministry has collected monthly data on nutrition-related indicators and other health conditions for many years.

Our multi-disciplinary team set out to explore whether we could use this data to help forecast where, geographically, child malnutrition was likely to occur in the near future. We were aiming for a more accurate forecast than the existing method.

We developed a machine learning model to forecast acute malnutrition among children in Kenya. A machine learning model is a type of mathematical model that, once “trained” on an existing data set, can make predictions of future outcomes. We used existing data and improved forecasting capabilities by including complementary data sources, such as satellite imagery that provides an indicator of crop health.

We found that machine learning-based models consistently outperformed existing platforms used to forecast malnutrition rates in Kenya. And we found that models with satellite-based features worked even better.

Our results demonstrate the ability of machine learning models to more accurately forecast malnutrition in Kenya up to six months ahead of time from a variety of indicators.

If we have advance knowledge of where malnutrition is likely to be high, scarce resources can be allocated to these high-risk areas in a timely manner to try to prevent children from becoming malnourished.

How we did it

We used clinical data from the Kenya Health Information System. This included data on diarrhoea treatment and low birth weight. We collected data on children who visited a health facility who met the definition of being acutely malnourished, among other relevant clinical indicators.

Given that food insecurity is a key driver of acute malnutrition, we also incorporated data reflecting crop activity into our models. We used a NASA satellite to look at gross primary productivity, which measures the rate at which plants convert solar energy into chemical energy. This provides a coarse indicator of crop health and productivity. Lower average rates can be an early indication of food scarcity.

We tested several methods and models for forecasting malnutrition risk among children in Kenya using data collected from January 2019 to February 2024.

The gradient boosting machine learning model – trained on previous acute malnutrition outcomes and gross primary productivity measurements – turned out to be the most effective model for forecasting acute malnutrition among children.

This model can forecast where and at what prevalence level acute malnutrition among children is likely to occur in one month’s time with 89% accuracy.

All the models we developed performed well where the prevalence of acute child malnutrition was expected to be at more than 30%, for instance in northern and eastern Kenya, which have dry climates. However, when the prevalence was less than 15%, for instance in western and central Kenya, only the machine learning models were able to forecast with good accuracy.

This higher accuracy is achieved because the models use additional information on multiple clinical factors. They can, therefore, find more complex relationships.

Implications

Current efforts to predict acute malnutrition among children rely only on historical knowledge of malnutrition patterns. We found these forecasts were less accurate than our models.

Our models leverage historical malnutrition patterns, as well as clinical indicators and satellite-based indicators.

The forecasting performance of our models is also better than other similar data-based modelling efforts published by other researchers.

As resources for health and nutrition shrink, improved targeting to the areas of highest need is critical. Treating acute malnutrition can save a child’s life.

Prevention of malnutrition promotes children’s full psychological and physical development.

What needs to happen next

Making these data from diverse sources available through a dashboard could inform decision-making. Responders could get six months to intervene where they are most needed.

We have developed a prototype dashboard to create visualisations of what responders would be able to see based on our model’s subcounty-level forecasts. We are currently working with the Kenyan ministry of health and Amref Health Africa, a health development NGO, to ensure that the dashboard is available to local decision-makers and stakeholders. It is regularly updated with the most current data and new forecasts.

We are also working with our partners to refine the dashboard to meet the needs of the end users and promote its use in national decision-making on responses to acute malnutrition among children. We’re tracking the impacts of this work.

Throughout this process, it will be important to strengthen the capacity of our partners to manage, update and use the model and dashboard. This will promote local responsiveness, ownership and sustainability.

Scaling up

The Kenya Health Information System relies on the District Health Information System 2 (DHIS2). This is an open source software platform. It is currently used by over 80 low- and middle-income countries. The satellite data that we used in our models is also available in all of these countries.

If we can secure additional funding, we plan to expand our work geographically and to other areas of health. We’ve also made our code publicly available, which allows anyone to use it and replicate our work in other countries where child malnutrition is a public health challenge.

Furthermore, our model proves that DHIS2 data, despite challenges with its completeness and quality, can be used in machine learning models to inform public health responses. This work could be adapted to address public health issues beyond malnutrition, like changes in patterns of infectious diseases due to climate change.

This work was a collaboration between the University of Southern California’s Institute on Inequalities in Global Health and Center for Artificial Intelligence in Society, Microsoft, Amref Health Africa and the Kenyan ministry of health.

– Child malnutrition in Kenya: AI model can forecast rates six months before they become critical
– https://theconversation.com/child-malnutrition-in-kenya-ai-model-can-forecast-rates-six-months-before-they-become-critical-261075