Project Manager

New multi-hotspot detection tech based on Lab* feature descriptor. A Husqvarna researcher developed a fast, interpretable PV hotspot-detection method using IR thermography and Lab* color-space features instead of heavy neural networks, achieving up to 95.2% accuracy with shallow classifiers. The lightweight system works in real time on drones or edge devices and could save 17,620 kWh and 8.9 tons of CO[2] annually by improving fault detection in solar panels. A researcher at Husqvarna Group, a Swedish outdoor power products manufacturer, has developed a novel, lightweight, and interpretable framework for a real-time PV fault-detection method. The technique employs infrared (IR) thermography and, rather than relying on common image feature descriptors based on high-dimensional texture, utilizes analysis in the uniform Lab* color space. Lab* is widely used in printing, photography, design, manufacturing, and color science because it is device-independent and perceptually uniform. By separating luminance (L) from chromaticity (a and b), it enhances the detection of surface-level degradations. "This work presents a novel, application-focused approach to multi-hotspot detection that departs from prevailing PV thermography trends," the researcher Waqas Ahmed told pv magazine. "Rather than relying on convolutional neural networks or high-dimensional texture descriptors, I propose a patch-wise feature extraction pipeline based on the perceptually uniform Lab* color space, producing a compact vector of 80 statistical descriptors per image." "The new design prioritizes interpretability, computational efficiency, and robustness to illumination and environmental variability, making it suitable for drone, handheld, and embedded edge deployments," Ahmed further explained. "It was surprising to see how the new technique achieved strong hotspot discrimination, even comparable to much heavier models, while remaining robust across varying illumination and survey conditions." The novel method begins by capturing IR thermographs of PV modules in operation at 640x512 pixels and converting them from their original channels to the L*, a*, b* color space. Each image is then sliced into 16 patches of 64x64 pixels to enable local fault detection. The system then extracts two statistics from the L* channel (mean and standard deviation) and three from the b* channel (mean, standard deviation, and entropy). Overall, each image yields 80 features, with five features extracted from each of the 16 segments. Accordingly, shallow classifiers can be trained to extract features. To demonstrate the new method, Ahmed has collected IR data from a 44.24 kW rooftop PV system located in Lahore, Pakistan. The system comprised 376 PV modules, each rated at 240 W, organized into eight strings, with 22 modules connected in series per string, for a total of 5.28 kW per string. Thermal imaging was conducted while ambient temperatures ranged from 32 C to 40 C, wind velocity was 6.9 m/s, and solar irradiance was at or above 700 W/m2. The researcher then categorized 309 IR thermographs as healthy, hot-spot, or faulty panels. The dataset was then randomly split into 80% for training (246 images) and 20% for testing (63 images), with equal representation of hotspot subtypes. Then, it was fed into a suite of shallow classifiers, namely SVM, KNN, Decision Tree, Naive Bayes, and Ensemble. SVM was found to achieve a test accuracy of 95.2%, KNN 93.7%, and the ensemble 90.5%. Naive Bayes achieved 84.1% test accuracy, and the decision tree achieved 81.0%. "The method demonstrates sub-6-second training latency on edge platforms and reports measurable system-level benefits preserving up to 17,620 kWh annually and mitigating 8.9 t CO[2], thereby linking algorithmic novelty to operational and environmental impact," Ahmed concluded. "My next work, together with my colleague Manahil Zulfiqar, will focus on label noise and misannotation in PV datasets for AI applications. We will investigate methods to detect and correct mislabeled examples, separate overlapping hotspot subclasses, and combine cross-modal consistency checks, uncertainty estimation, and active relabeling to improve field reliability." The new method was presented in "Thermal and chromatic analysis for scalable photovoltaic hotspot detection," published in Solar Energy. Ahmed is affiliated with Sweden's Husqvarna Group, Jönköping University, and the United Kingdom's Imperial College London. This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: [email protected].

Urban Green Space continues to decline globally- Nordic Region emerges as a green hub. News provided by. STOCKHOLM, Nov. 19, 2025 /PRNewswire/ - Husqvarna Group today presents the Urban Green Space Insights (HUGSI) Report 2025, which uses AI and satellite data to measure green spaces in cities worldwide. The report reveals that the 516 cities analyzed have lost green areas equivalent to nearly the size of Paris. In contrast, the Nordic region stands out as a green hub, hosting some of the greenest cities globally. Since 2019, Husqvarna Group's HUGSI has provided objective data on urban green space development. HUGSI's tools are used in international research and serve as a foundation for city planning decisions. This year, a total of 516 cities in 80 countries on six continents have been analyzed on each city's greenest day of the year, offering valuable insights into how urban greenery has evolved over time. The analyzed cities range from 5,000 inhabitants in Netherlands to mega cities like Chongqing in China with over 30 million inhabitants. The average green coverage ranges from 25% in South & West Asia to 46% in Europe. For instance, Riyadh (Saudi Arabia), has only 1% green coverage, while several European cities boast more than 60% of greenery. "As urbanization accelerates, understanding how green spaces change is essential for creating sustainable, livable cities. Active development of urban greenery should always be a priority when planning public infrastructure," says Erik Swan, green space specialist and project manager for HUGSI at Husqvarna Group. Global Trend: Loss of Green Space Equivalent to Paris Between 2023 and 2024, the analyzed cities recorded a loss of 95 million m[2] of green space - almost the size of Paris - primarily due to human activities such as construction and urban expansion. Among the analyzed cities, 73% show a negative development. On the positive side, 45 million m[2] of new or improved green space was added, mostly through expanded grass cover, likely driven by weather conditions and other passive factors rather than active greening efforts. Cities in the Northern Hemisphere generally have more green space than those in the Southern Hemisphere. Europe maintains the highest average share of urban greenery globally at 46%. Despite this, the net change in 418 European cities is negative: 17 million m[2] gained versus more than 30 million m[2] lost, resulting in a net loss of 13.3 million m[2] - equivalent to over 1,800 football fields. Among European cities, Aarhus (Denmark), Sunderland (UK) and Chisinau (Moldova) show significant increases. Vilnius again tops the list of European capitals with 61% green space, 226 m^2 per capita, and 47% tree canopy cover. Nordic Region: A Global Green Leader The Nordic cities stand out with an impressive 49% share of urban green space (compared to Europe's 46%), meaning nearly half of the urban land area in the 40 largest Nordic cities is covered by vegetation - trees, grass and shrubs. The region also shows lower green space loss than Europe overall, with a net decrease of 385,000 m^2. Vejle in Denmark is the greenest Nordic city (58% green space), followed by Uppsala and Linköping in Sweden. Aarhus leads Europe in net positive change, adding almost 1,2 million m[2] of greenery. The Nordics also shine globally with an average urban tree canopy cover of 35%. Finland ranks highest at 44%, while Denmark has fewer urban trees (24%) but some of the greenest cities overall with 48% green space. "Green spaces are the lungs of the city. Trees play a vital role in urban environments - they reduce temperatures through shade, improve air quality, support biodiversity and contribute to the mental and physical wellbeing of city residents", adds Erik Swan. To learn more about the methodology and the results, please find the reports here: