When severe weather disrupts communities, digital connectivity can become an essential lifeline. Communication networks support emergency response, keep critical services operating and help communities remain connected when physical infrastructure is under pressure. Their value can easily go unnoticed during normal conditions, but becomes immediately apparent when connectivity is interrupted.

This year's World Telecommunication and Information Society Day theme, “Digital lifelines – Strengthening resilience in a connected world,” highlights the growing importance of resilient digital infrastructure. Climate change is no longer simply an environmental issue. Increasingly, it represents a direct operational challenge for organizations and societies that depend on interconnected physical and digital systems.

Climate change is increasingly being experienced through severe storms, flooding, extreme heat and wildfires. These events can place significant and immediate pressure on power systems, communications networks and other essential infrastructure.

Nokia and CGI are conducting a joint assessment examining how extreme weather could affect connectivity infrastructure in the United States and India. The study draws on several sources of information, including World Bank projections, EM-DAT disaster records and primary survey data.

Early findings indicate that extreme weather events are not only becoming more intense but are also occurring in more concentrated and extended patterns. This can create multiple, overlapping pressures on infrastructure rather than producing isolated disruptions.

In the United States, the research identifies an upward trend in severe storm activity. Peak years have recorded as many as 23 major storm events, accompanied by increasingly intense and concentrated rainfall.

In India, the assessment points to growing flood exposure associated with heavier rainfall. The number of days receiving more than 50 mm of rain is projected to increase substantially over the longer term, potentially reaching up to seven times the levels seen in shorter-term baseline periods. At the same time, pre-monsoon temperatures are becoming more persistent and intense.

Higher-emission scenarios amplify these risks in both countries. The findings suggest that extreme weather is increasingly capable of placing sustained, systemic pressure on critical infrastructure rather than causing occasional, isolated interruptions.

Climate adaptation is therefore an ongoing process, while climate resilience represents the desired outcome: infrastructure and services that can anticipate disruption, withstand shocks, recover efficiently and adapt to changing conditions. Technology has an important role in enabling that resilience.

Nokia views resilience as the ability of critical systems — including connectivity, energy and public services — to remain operational during periods of severe environmental stress. These systems must also be considered as interconnected networks rather than as individual components operating independently.

The company's approach centers on three areas:

Artificial intelligence is an important enabler across each of these areas. AI can help systems identify potential disruptions, respond dynamically to changing conditions and accelerate recovery. Resilience must also be developed responsibly, with energy efficiency, circularity and careful resource management remaining important considerations so that sustainability and resilience progress together.

The Nokia–CGI assessment identifies several ways extreme weather can affect communications infrastructure.

Higher temperatures and environmental conditions can reduce the performance of communications equipment, while storms and flooding can physically damage network assets. Dependence on electrical grids can also cause a localized infrastructure problem to spread across wider areas. Meanwhile, dangerous conditions and limited physical access can make repairs and recovery more difficult.

Nokia's role includes providing technologies that help customers prepare for, withstand and recover from these disruptions. These capabilities can support business continuity, reduce operational risks and protect long-term economic value. They include:

Ultimately, resilience is about more than keeping infrastructure operational. It is about protecting people and helping communities function during periods of uncertainty.

When communications networks remain available, emergency calls can be completed, hospitals can stay connected, families can communicate and authorities can coordinate response and recovery efforts. Reliable connectivity can therefore have effects that extend well beyond the technology itself, supporting social stability when communities face major disruptions.

Building this level of resilience requires cooperation. No single organization can address the challenge alone. Operators, governments, humanitarian organizations and technology partners must work together to develop and deploy solutions that can strengthen connectivity and reach the communities and locations that need them most.

Click here to know more.

Portable screen-printed carbon electrode (SPCE) biosensors provide a fast and cost-effective solution for detecting microcystin-LR (MC-LR), one of the most toxic compounds released by cyanobacteria during harmful algal blooms in freshwater ecosystems. Even at very low concentrations, MC-LR poses serious health risks, including liver damage, and has been associated with a higher likelihood of liver and colorectal cancers. To protect public health, the World Health Organization recommends that drinking water contain no more than 1 microgram of MC-LR per liter.

These biosensors estimate toxin levels by monitoring changes in electrochemical signals generated when MC-LR is present. However, their performance is often influenced by the characteristics of the water sample itself. Variations in pH, turbidity, electrical conductivity, and other water quality parameters can alter sensor responses, making it necessary to recalibrate the device for each individual sample.

A research team from Hanbat National University in South Korea and the University of Central Florida in the United States has developed a machine learning-based approach that overcomes this limitation by compensating for differences in water quality. The study, led by Professor Jungsu Park of Hanbat National University and Professor Woo Hyoung Lee of the University of Central Florida, was first published online on 26 March 2026 before appearing in Volume 298 of Water Research on 15 June 2026.

According to Professor Park, "This work provides a robust data-driven framework for characterizing biosensor-water matrix interactions and offers a practical approach to improving the speed and accuracy of on-site MC-LR detection in complex environmental waters."

To develop the predictive model, the researchers gathered 201 datasets from 27 sampling locations across Florida, covering freshwater, estuarine, and transitional water bodies with diverse environmental conditions. For every sample, they recorded key water quality indicators—including pH, turbidity, electrical conductivity, total dissolved solids, ultraviolet absorbance at 254 nanometers (UV254), and the biosensor's electrochemical impedance (Z'), which varies with MC-LR concentration. These measurements served as model inputs, while laboratory-determined MC-LR concentrations were used as the target outputs.

The team evaluated several machine learning algorithms, with the Extreme Gradient Boosting (XGBoost) model delivering the strongest performance. It achieved a Nash-Sutcliffe efficiency of 0.89 and a root mean square error of 13.21, demonstrating that a single generalized model could accurately estimate MC-LR concentrations across a wide range of water conditions without the need for sample-specific calibration.

To better understand how different variables contributed to the model's predictions, the researchers employed Shapley Additive Explanations (SHAP), an explainable artificial intelligence technique. Their analysis revealed that the biosensor's electrochemical impedance had the greatest influence on prediction accuracy, followed by electrical conductivity, pH, UV254 absorbance, and turbidity. These findings highlight the importance of incorporating water quality characteristics into the predictive framework to improve biosensor reliability.

Professor Park noted, "This framework eliminates the need for repeated sample-specific calibration, reducing time, labor, and sensor consumption. Compared to conventional workflows, it can reduce sensor usage and thereby lowering cost and environmental burden while improving analytical efficiency."

With climate change contributing to an increase in the frequency and severity of harmful algal blooms, this machine learning-assisted biosensing approach has the potential to make monitoring of toxic cyanobacterial contaminants faster, more accurate, and more practical for routine testing of drinking water supplies and recreational water bodies.