Introduction.

Accurate meteorological intelligence is crucial in Africa as the continent is (increasingly) exposed to the effects of climate change and variability. In the context of this article, meteorological intelligence is a collective term for weather and climate intelligence.

According to the Intergovernmental Panel on Climate Change (IPCC), Africa is the most vulnerable continent to climate change because of its high exposure to climate stress and low adaptive capacity. The State of Climate in Africa 2022 report highlights the severe damage of climate change in Africa.

The floods that ravaged Central, Western, and East Africa affected the lives of over 1 million people. The tropical storms and cyclones that hit Southern Africa affected over 2.5 million people, resulting in the death of more than 600 people.

The northern part of Africa experienced disasters associated with extreme temperature anomalies, from the heatwaves and wildfires that raged in Tunisia, Morocco, and Algeria to the heavy rainfall, snow, and sandstorms that plagued Libya.

With most of these disasters happening without warning, it is safe to say that the unavailability of accurate meteorological intelligence has left Africa at the mercy of Mother Nature. While the debilitating effects of these disasters will remain for years, WiHi is proffering a solution to prevent the unpredicted and without-warning recurrences of these disasters.

WiHi is a web3 company providing accurate meteorological intelligence everywhere, anytime. This article will discuss WiHi and its methodology for actionable meteorological intelligence in Africa.

Understanding the factors hampering accurate meteorological intelligence in Africa.

Weather is the state of the atmosphere in a particular location at any period. Climate is the average weather pattern of a place over a long period, usually 30 years or more. Meteorological intelligence is the collection and maintainability of accurate real-time weather/climate data necessary for making accurate forecasts.

These forecasts contain enough information to facilitate the implementation of policies necessary to mitigate the physical and economic risks associated with climate change. From the definition above, we can split meteorological intelligence into two parts: collection and maintainability of quality meteorological data and accurate forecasting based on the data collected.

The scarcity of quality meteorological data is the major obstacle hindering the achievement of accurate meteorological intelligence in Africa. Insufficient meteorological data has significant repercussions in measuring the extent of climate change. Also, without reliable weather records, it becomes challenging to fine-tune weather models or develop higher-quality climate models.

In particular, meteorologists cannot provide reliable forecasts or timely warnings about potential climate extremes. In the State of Climate in Africa 2022 report, Prof. Petteri Taalas, former Secretary-General of the World Meteorological Organization (WMO), addressed the problem of climate data unavailability.

Climate data is critical for developing climate services that support informed decision-making. Nevertheless, significant gaps in basic weather and climate observations remain over Africa.

Prof. Petteri Taalas.

There are two major causal factors of quality meteorological data scarcity in Africa. They include a steady decline in the number of operational weather stations in Africa and the poor quality of data collected by functional weather stations. Despite facing significant natural disasters annually, Africa struggles with an outdated and deteriorating weather infrastructure system.

To further exacerbate this issue, Africa has the lowest coverage of weather observation networks, presenting a challenge in generating reliable data to mitigate the impact of climate change on the continent. According to the World Bank, Africa has the least developed weather, water, and climate observation network in the world, with less than 300 of its weather stations meeting the World Meteorological Organization (WMO) observation standards.

Furthermore, 54 percent of its surface weather stations and 71 percent of its upper-air weather stations do not report accurate data. Based on the WMO database, Europe and the United States have a combined total of 636 weather radar stations for a population of 1.1 billion people. Africa, with a population of 1.2 billion people, has 37 weather radar stations variably distributed across the continent.

In Chapter 7 of the book Extreme Hydrology and Climate Variability, Tufa Dinku highlights declining investment, social or political conflict, and remote geography as the reasons for sparse climate observation networks in Africa. The lack of sufficient funding hinders the operation and maintenance of climate observation networks and related infrastructure.

One of the reasons behind this is the challenges in effectively harnessing the value added by these networks. In particular, policymakers may exhibit shortsightedness, lacking a long-term perspective on the benefits of climate observations in developing an environmentally resilient region.

Political unrest, such as the ongoing conflicts in Nigeria, can destroy operational weather stations, rendering accurate data collection difficult. The high insecurity in conflict zones discourages organizations from setting up new weather stations, as it poses a risk to the lives of their employees.

Geographical factors, such as challenging terrains like mountains, forests, and deserts, contribute to the sparse distribution of weather observation networks across the continent. The difficulty in installing and maintaining weather stations in these areas limits the overall number of weather stations.

Additionally, the dispersed nature of rural populations, especially in lowland areas, makes the setup of weather stations economically unprofitable. National planners may prioritize placing stations in cities with high concentrations of people and economic activity, overlooking the need for comprehensive spatial coverage in rural or difficult-to-access areas.

Apart from the handful of operational stations available to collect meteorological data, the quality of the data collected also poses a significant challenge in producing accurate forecasts. Poor data quality arises from poor accuracy, imprecise measurements, and missing observations.

Station measurements used to collect meteorological data are susceptible to errors. These errors may stem from human mistakes, faulty instruments used for measurements, or other factors that can affect the reliability of the collected data.

Mistakes made during data entry are another common source of error that can compromise the accuracy and reliability of the information stored in databases. Zero implementation of quality control for collected data reduces the quality of meteorological data.

The absence of skilled personnel or training on existing data quality tools can hinder the proper implementation of quality control measures. The following section will cover WiHi's approach to solving these problems to improve accurate meteorological intelligence in Africa.

A deep dive into WiHi.

What is WiHi?

WiHi is a Solana-based platform focused on providing accurate meteorological intelligence everywhere in the world, anytime, by establishing an incentivized collaboration between all actors in the meteorological sector (global and local).

WiHi achieves this by integrating them into a community-owned infrastructure and linking it to the consumer market, which currently has an unfulfilled need for weather data and forecasting valued at 11.5 billion USD.

What makes WiHi stand out amongst other meteorological entities? While other companies are piggybacking on public/ governmental institutions' work and focused on generating their data and producing forecasts at high price points, WiHi positions itself in the intersection by being a platform for all, public, private, and hobbyist meteorological entities where they can meet and collaborate, sharing data and producing pinpoint accurate forecasts, effectively sharing the revenues of the the weather forecasting market.

How does WiHi work?

Since WiHi is open-hardware, entities that own weather stations will configure their stations to stream observed data to the WiHi protocol. The protocol then rewards them with WiHi tokens for doing so via a usage reward that accounts for the quality and usefulness of the data.

For forecasting, WiHi is currently using its proprietary AI/ML model to produce accurate forecasts based on the data streamed to the protocol. At the moment, WiHi uses a centralized forecasting model. In the future, WiHi will use the collective intelligence of the weather community for its forecasting by decentralizing and incentivizing third parties to commit forecasts to the platform.

This will improve the quality of the single forecasts by aggregating them into ensemble forecasts. It is known from the Netflix challenge, that aggregating superior forecasts with inferior forecasts improves the former significantly, a phenomenon called collective intelligence in the complexity sciences.

WiHi intends to use a gamified reward system for the forecasters leveraging mechanisms from cryptoeconomics such as staking or auction markets. If the data used to make the forecast was from a WiHi-enabled weather station, the station gets rewarded because only quality data can produce accurate forecasts.

This gamified approach solves two problems: low-quality forecasts and low-quality data. Since forecasters are looking for ways to covet the price, they will only use quality data to compute their predictions. WiHi-enabled weather stations will also improve their data quality control measures to get rewards for collecting the most qualitative dataset for the forecasts.

Also, third-party weather data buyers will only purchase quality data. The winning streaks of a weather station or forecaster on the protocol is the best way to prove the quality of datasets and forecasts.

Improving meteorological intelligence in Africa through WiHi.

This section will discuss the achievable solutions WiHi can proffer to some of the problems hampering meteorological intelligence in Africa. One of the problems WiHi will tackle is the sparse distribution of weather stations in Africa.

Through its ambassador program, WiHi will provide funding to its ambassadors to install and maintain weather stations in areas without one. If this is successful, with time, the number of observation stations in Africa will increase, forming a dense observation network across the continent.

This solution will also tackle the preferential treatment of national planners towards urban settlements when it is time to install new weather stations. The problem of low-quality data is the easiest to solve. How? Most organizations are nonchalant towards processes that can increase the quality of data collected because they are not getting rewarded for doing so.

The WiHi model rewards stations collecting high-quality data while flagging stations collecting low-quality data to potential data buyers and other entities in the meteorological sector. With the knowledge of getting rewards for high-quality data collection or losing credibility and reputation for low-quality data collection, these organizations will eventually improve their data control measures.

Conclusion.

WiHi can greatly enhance meteorological intelligence in Africa, giving countries a crucial edge in preparing for extreme climate events and reducing the associated physical and economic risks. According to the World Bank, the provision of accurate meteorological intelligence can save US$22 billion in losses to well-being, and US$30 billion through a resulting increase in productivity and this is what WiHi intends to achieve in Africa.

As the adoption of the WiHi grows, we are bullish about the positive changes it will bring. To learn more about WiHi and stay updated with the latest happenings about it, visit their website, join their discord server, follow on Twitter or Linkedln, ask the right questions, and become part of the w3ather movement.