Sub-headline: HIT (Shenzhen) researchers develop FedPD to enhance personalized cross-architecture collaboration

Researchers from Harbin Institute of Technology (Shenzhen) proposed FedPD, a personalized federated learning method based on partial distillation. By assessing knowledge relevance for selective transfer, FedPD enables efficient collaboration among clients with diverse model architectures while significantly improving performance on heterogeneous data.

A detailed econometric analysis of Bangladesh from 1974 to 2022 offers new quantitative insights into the complex drivers behind the nation's rising carbon dioxide emissions. Researchers from the National University of Malaysia, University of Chittagong, Noakhali Science and Technology University, and Bangladesh University of Engineering and Technology examined the long-term relationships between CO₂ emissions and four key pillars of the economy: economic growth, energy consumption, financial development, and natural resource rents. The investigation confirms that while these factors are essential for national development, they currently contribute directly to environmental degradation, presenting a critical challenge for achieving sustainability goals.

Privacy-preserving feature selection allows identifying more important features while ensuring data privacy, thus enhancing data quality. Secure multiparty computation (MPC) is a cryptographic method that allows effective data processing without a trusted third party. However, most MPC-based feature selection schemes overlook the correlation between features and perform poorly for model training when handling datasets containing both numerical and categorical attributes.

Forest ecosystems stand as indispensable regulators of the planet’s climate, actively influencing atmospheric greenhouse gas (GHG) emissions and thereby affecting global warming. A recent study by researchers at the University of Debrecen provides a comprehensive evaluation of these emissions from various sources within forested landscapes. The investigation assesses their individual contributions to global warming potential (GWP), delivering crucial insights for shaping climate policies, advancing carbon accounting, and implementing sustainable forest management practices. This work is essential for developing more precise strategies to mitigate climate change and deepening our scientific understanding of ecosystem-climate dynamics.

To achieve its objectives, the research employed a rigorous analytical framework, utilizing comprehensive data from the EDGAR—Emissions Database for Global Atmospheric Research, spanning from 1990 to 2022. This extensive dataset enabled the team to meticulously analyze emissions of carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O) originating from deforestation, forest fires, and natural processes such as organic soil decomposition. The study leveraged time series analysis and an ARIMA model to identify trends, project emission trajectories until 2030, and quantify CO₂ equivalent emissions for each category. Further, correlation analysis illuminated the intricate relationships between various emission sources, offering a holistic perspective on terrestrial carbon dynamics.

A comprehensive new analysis of South Africa's environmental footprint reveals a complex and often contradictory relationship between development and pollution. Researchers Frank Ranganai Matenda, Helper Zhou, and Mabutho Sibanda from the University of KwaZulu-Natal, alongside Asif Raihan of the National University of Malaysia, examined three decades of national data to untangle the key drivers of carbon dioxide (CO₂) emissions. The investigation, spanning from 1990 to 2020, exposes how economic progress, globalization, and even technological innovation are currently contributing to rising emissions, while highlighting the significant potential of renewable energy to reverse this trend.

Applying biochar to soil is a recognized strategy for combating climate change, primarily by locking away carbon for long periods. Yet, its broader impact is complex; under different conditions, biochar can either suppress or unexpectedly release other potent greenhouse gases like nitrous oxide and methane from the soil. This inconsistency has been a significant barrier to its widespread adoption. A new set of predictive models developed by researchers Beatriz A. Belmonte, Raymond R. Tan, and their colleagues at the University of Santo Tomas and De La Salle University brings clarity to this issue. The team created a system to predict how soils will respond to biochar, offering a way to tailor its application for maximum climate benefit.