Renewable Energy Research In Science

India has its first fully solar-powered village: Manyachiwadi Manyachiwadi is a tiny village in Maharashtra’s Satara district, home to just 420 residents. And yet, they achieved what most towns in India still haven’t. - Every single home has rooftop solar panels - 102 installations power homes, a school, the gram panchayat, public water supply, CCTV, and even streetlights - Not one electricity bill. In fact, they send power back to the grid. - No paper bills. They’ve gone 100% green - RCC roads, clean drainage, CCTV networks, and soon, agritourism. But here’s what truly makes Manyachiwadi special: This solar revolution was led by women. Back in 2010, tired of long power cuts, the women, mostly farmers and homemakers pooled their savings, called gram sabha meetings, and started installing basic solar lamps. By 2019, every home had two solar-powered LED lights. And in 2024? Every roof is a mini power plant. No more 8-hour outages and no more kids studying by kerosene lamps. And definitely no waiting around for “someone else” to fix things. From ₹1 crore in government subsidies, to weekly gram sabha meetings, to young boys doing homework under bright, clean light. Manyachiwadi is proof that community beats complexity. This is what happens when politics take a backseat and progress leads. No sarpanch elections in 30 years,just consensus, clarity, and collective will. The question isn’t how they did it. The question is ,why haven’t we? Would you invest in a village that wants to light up its future, just like Manyachiwadi did? Link in the comments.

Norway Converts Deep Ocean Pressure Into Electricity Using Subsea Energy Vaults Norwegian researchers have completed successful trials of a revolutionary underwater energy storage system that uses deep-sea pressure to generate power on demand — offering a clean alternative to batteries in coastal grids. Installed off the coast of Bergen, the system consists of massive hollow spheres anchored 400 meters below the surface, which can store and release energy using water and gravity alone. The process is mechanically simple but incredibly effective. When surplus wind or hydro power is available, electricity is used to pump water out of the spheres against immense ocean pressure. When energy is needed later, valves open and water rushes back in, spinning turbines to generate electricity — just like a hydro dam, but inverted and underwater. The pilot system achieved a round-trip efficiency of 80% during six months of continuous cycling. Because the surrounding water pressure is so high, the system can store large amounts of energy in a small volume — making it ideal for islands, offshore wind farms, or areas with unstable grids. Unlike lithium-ion batteries, this subsea system is made of concrete and steel, doesn’t degrade with use, and poses no fire or chemical risk. It’s also invisible — a critical feature for environmentally sensitive marine zones. Norway’s invention turns the crushing power of the deep ocean into a silent, emission-free energy reservoir — a hidden battery beneath the waves.

Interesting new Fraunhofer IWES study shows significant cost saving potential of European wind offshore cooperation 📜 𝐁𝐚𝐜𝐤𝐠𝐫𝐨𝐮𝐧𝐝 German waters, particularly in the North Sea, get increasingly crowded – with substantial wake effects leading to low wind generation and thus high Levelised Cost of Electricity (LCOE). In this context, the idea emerged to reduce the targets for wind offshore buildout in the German Exclusive Economic Zone (EEZ), and instead build more in the EEZs of neighbouring countries with more space and wind, but connect these with electricity subsea cables to Germany (“radial connection”). 💡𝐒𝐭𝐮𝐝𝐲 𝐫𝐞𝐬𝐮𝐥𝐭𝐬 A new study by Fraunhofer-Institut für Windenergiesysteme, commissioned by BDEW Bundesverband der Energie- und Wasserwirtschaft e.V. and BWO - Bundesverband Windenergie Offshore e.V., analysed the effects of such international cooperation on wind output and cost. Key insights: Moving up to 20 GW to Danish & Swedish seas (Scenario 2) leads to 👉 up to 13% higher wind yield 👉 up to 11% lower system cost (incl. grid connection cost) 👉 stronger security of supply 🔗Study available here: https://lnkd.in/eAXZzKfV Interestingly, the German government had already anchored this approach in their coalition agreement. Talks with neighbouring countries are starting. ⏭️ 𝐅𝐨𝐥𝐥𝐨𝐰-𝐮𝐩 𝐰𝐨𝐫𝐤 𝐛𝐲 𝐅𝐫𝐨𝐧𝐭𝐢𝐞𝐫 BDEW & BWO asked us (Frontier Economics) to use the Fraunhofer results as input to analyse how to most cost-effectively connect these offshore wind parks, with a particular view on how much ‘overplanting’ is sensible. Watch the space.

A State-of-the-Art Review on Geothermal Energy Extraction, Utilization, and Improvement Strategies: Conventional, Hybridized, and Enhanced Geothermal Systems This paper presents a review the potential of geothermal energy,  technologies implemented in power plants and direct heat applications; performance enhancement of the existing conventional systems, the implementation of Enhanced Geothermal Systems (EGS) and Hybridized Geothermal Systems. Main takeaways: ✔ the larger geothermal capacity factor necessitates faster geothermal development. Accelerating EGS development would be a significant accomplishment ✔ recently, there has been considerable interest in hybrid systems that combine geothermal and other energy sources to increase the output efficiency of a geothermal system. Geothermal energy shows great potential when utilized in combination with some other form of renewable resource. ✔ geothermal energy systems have proven to be highly effective in establishing a more balanced power supply #geothermal #energy #renewable #heat #electricity #hybridization #EGS #Enhanced #Geothermal #Systems

"Why is conventional geothermal not the answer? It’s restricted by geology. Conventional geothermal tends to work only in a few locations around the world with a high thermal gradient, tapping into shallow, high-heat resources. Wells are drilled into highly permeable reservoirs, drawing the hot fluids to surface where they generate the power and heat in the geothermal plant. Just 0.6% of the 45,000 oil and gas reservoirs in our database have these qualities. What are new technologies trying to do that’s different? Take geothermal global and realise the aspiration of geothermal anywhere. The holy grail is wells that can work in locations with an average thermal gradient. Two technologies are targeting low permeability rocks. Enhanced geothermal systems (EGS) use fracking to stimulate the flow of hot fluids through the rocks; advanced geothermal systems (AGS) are testing closed-loop designs where water or other fluids are circulated through the hot rock without leaving the wellbore. Separately, a range of new drilling technologies are hoping to cut well costs, which account for up to 90% of geothermal project capital expenditure. Non-drilling projects include more effective heat exchangers to maximise output from lower temperature resources and co-location of geothermal with hydrogen production, direct air capture, underground thermal energy storage and critical mineral extraction to maximise the value of the geothermal resource. Most of the pilot projects are in Europe and the US where there are subsidies available. The level of spend on the pilot projects is currently tiny, amounting to just a few hundred million dollars. But if geothermal goes global, we estimate that cumulative investment through 2050 could be US$1 trillion. Which projects could signal the breakthrough? Both EGS and AGS technologies are being tested at commercial scale and could be moving towards widespread, location-agnostic deployment. Eavor’s AGS project at Geretsreid in Germany is one to watch. Its Eavorloop multilateral closed-loop well design is targeting 60 MWth of heat capacity and 8.2 MW of power by 2026 from a reservoir at 4.5 kilometres depth with a normal geothermal gradient. Success could see five similar installations following in short order. Another is Fervo Energy’s Project Red in Nevada which came onstream in 2023 and has already demonstrated EGS technologies at commercial scale. Its much larger Project Cape in Utah began drilling 29 wells in 2023 and aims to produce 400 MW from EGS by 2028. Both harness the much higher-than-average geothermal gradients in these locations. Are costs a challenge? Yes. Geothermal’s current levelised cost of electricity is well out of the money at about US$200/MWh. Should the pilot projects prove the concept, the hope is that scaling up lowers the LCOE by two-thirds to US$75/MWh by 2050." https://lnkd.in/gaK65ehR

🗺️ Could weather maps be treated as word tokens for renewable energy forecasting? Since both energy production and language are sequences, the idea is to encode weather maps as embeddings, just as NLP does with word tokens, and then use a transformer to forecast the entire sequence. This makes it possible to combine spatial and temporal information within a single architecture: - Weather maps are encoded with a lightweight CNN. - Token sequences are processed with a transformer encoder. - The model learns to forecast wind or solar power. The same architecture can handle both wind and solar inputs without any modification. Traditional computer vision approaches often struggle with solar data due to night hours that carry no information. This formulation handles them naturally. Key results compared to ENTSO-E operational forecasts: 🌬️ Wind: ~63% reduction in forecast error ☀️ Solar: ~21% reduction in forecast error The model is lightweight (274k parameters, ~1 MB), fast to train (1–2 hours on a single A100), and scalable to any region or weather input without architectural changes. This work is part of the Weather4Energy project. ICSC - Centro Nazionale di Ricerca in HPC, Big Data e Quantum Computing | CINECA | IFAB - International Foundation Big Data and Artificial Intelligence for Human Development | Illumia

Beyond the Hype: A Clear-Eyed Look at Geothermal’s Role in the Energy Transition I spent months digging into geothermal, publishing many articles and ending with a just released full report, Beyond the Hype: Geothermal in Context, published by TFIE Strategy in late September 2025. Link to report PDF: https://lnkd.in/gDwz8G_n The work was shaped by open debate with engineers, scientists, investors, and policymakers who challenged assumptions and added missing context. The report separates proven approaches from hype. Conventional geothermal works in the right geographies but will always be limited. Enhanced and ultra-deep drilling carry stacked risks that mirror nuclear-scale megaprojects, where Flyvbjerg’s iron law of cost overruns is the norm. Closed-loop designs like Eavor deserve credit for ingenuity but remain constrained by efficiency, thermal depletion and first-of-a-kind drilling risks. Where geothermal already delivers value is in heating and cooling. China’s district heating buildout shows how shallow and medium-depth systems can scale, while seasonal thermal storage in Denmark and Alberta demonstrates real-world reliability. Industrial heat pumps with aquifers are cutting fossil demand today, and even data center cooling has niche but proven applications. The report urges policymakers to back shallow geothermal, district heating, and industrial heat while avoiding speculative drilling traps. Utilities should study Sinopec’s pivot to heat networks instead of clinging to stranded gas pipelines. Investors need to recognize where capital will be stranded and where it will deliver steady returns. The report is freely available for these audiences with the hope that it will aid them to make better decisions. Geothermal’s strength is not in competing with wind and solar on electricity, but in providing flexible, distributed, and dependable heat. In the right contexts, it simply works.

One of my all-time favorite A.I. researchers, Dr. Jason Yosinski, is my guest today! He details how his startup is using ML to collect wind energy more efficiently and digs into visualizing/understanding deep neural networks. Jason:  • Is Co-Founder and CEO of Windscape AI, a startup using ML to increase the efficiency of energy generation via wind turbines. • Is Co-Founder and President of the ML Collective, a research group that’s open to ML researchers anywhere. • Was a Co-Founder of the A.I. Lab at the ride-share company Uber. • Holds a PhD in Computer Science from Cornell, during which he worked at the NASA Jet Propulsion Laboratory, Google DeepMind and with the eminent Yoshua Bengio in Montreal. • His work has been featured in The Economist, on the BBC and, coolest of all, in an XKCD comic! Today’s episode gets fairly technical in parts so may be of greatest interest to hands-on practitioners like data scientists and ML engineers, although there are also parts that will appeal to anyone keen to hear how ML is being used to produce more clean energy. In today’s episode, Jason details:  • How ML can make wind direction more predictable, thereby making wind turbines and power grids in general more efficient. • How to infer what individual neurons in a deep learning model are doing by using visualizations. • Why freezing a particular layer of a neural net prior to doing any training at all can lead to better results. • How you can get involved in a cutting-edge research community no matter where you are in the world. • What traits make for successful A.I. entrepreneurs. Many thanks to Crawlbase for supporting this episode of Super Data Science, enabling the show to be freely available on all major podcasting platforms as well as the video version we publish on YouTube. This is Episode #789! #superdatascience #machinelearning #ai #climatechange #windenergy

Yesterday, I saw what tomorrow holds for India—a future growing on the land of Mr. Nirmal Das Swami, a farmer in Rajasthan.   Through a government program, Nirmal transformed his 9 hectares of farmland into a solar powerhouse, generating 1.04 megawatts of clean energy.    The impact? Beyond his crops and income, it’s lighting up his entire community:   → Salim, a welding business owner, doubled his working hours and revenue—hiring 6 new workers. → Firoz, a flour mill owner, increased daily production from 500 to 1,000 kg and is employing more people. → Women farmers like Gita, Anju, and Ghisi no longer have to wake up in the middle of the night, the only time power was previously available, to irrigate their crops.   Daytime power has replaced erratic nighttime electricity, enabling livelihoods to thrive.   Rajasthan is proof that changing energy changes lives, especially in rural India.   Today, India is betting big on a just energy transition—by deploying 500 gigawatts of renewable energy by 2030.    So far, they’ve achieved over 200 GW. Partnerships like the Global Energy Alliance for People and Planet (GEAPP), of which The Rockefeller Foundation is a member, are paving the way for even greater innovation and impact. For example, GEAPP is supporting 59 solar plants like Nirmal’s, providing 108 megawatts in support of 30,000 farms and enhancing 64,000 jobs across Rajasthan.   This kind of work doesn’t just transform lives—it transforms entire communities.   This is more than a story of one village. This is the future of India.