Skip to content
GCC AI Research

Search

Results for "decomposition"

Turning spoiled food waste into commercial products

KAUST ·

KAUST researchers have developed a technology to convert spoiled dairy and fruit beverages into valuable short-chain and medium-chain carboxylic acids (SCCAs and MCCAs). These acids can be used for animal feed, aviation fuel, and pharmaceuticals, with SCCAs valued at $300 per ton and MCCAs having 10x higher value. A pilot study is underway at KAUST, utilizing over 500 liters of waste per week from regional companies. Why it matters: This innovation supports Saudi Arabia's goal to eliminate 90% of landfill waste by 2040 and promotes a circular economy by transforming food waste into high-value products.

Wind Speed Forecasting Based on Data Decomposition and Deep Learning Models: A Case Study of a Wind Farm in Saudi Arabia

arXiv ·

A novel wind speed forecasting (WSF) framework is proposed combining Wavelet Packet Decomposition (WPD), Seasonal Adjustment Method (SAM), and Bidirectional Long Short-term Memory (BiLSTM). The SAM method eliminates the seasonal component of the decomposed subseries generated by WPD to reduce forecasting complexity. The model was tested on five years of hourly wind speed observations acquired from the Dumat Al-Jandal wind farm in Al-Jouf, Saudi Arabia, achieving high forecasting accuracy.

Reducing waste and improving soil

KAUST ·

Edama Organic Solutions received $780,000 USD seed investment from the KAUST Innovation Fund. KAUST has also signed a contract to build a commercial-scale composting facility for Edama on its Thuwal campus, with a recycling capacity of 5,500 tons. Edama will manufacture and sell products, including Edama Desert Compost and Edama Palm Peat. Why it matters: This initiative promotes sustainable waste management practices in Saudi Arabia by turning organic waste into valuable soil improvement products tailored for desert environments.

New study reveals star role of seaweed in struggle against climate change

KAUST ·

KAUST researchers from the Red Sea Research Center (RSRC) and Computational Bioscience Research Center (CBRC) found macroalgae DNA prevalent in the open ocean, up to 5,000 km from coastal areas. 69% of drifting macroalgae sinks below 1,000 m depth, sequestering carbon in deep ocean waters. The study used metagenomes generated by global ocean expeditions Tara Oceans and Malaspina, analyzed via KAUST's DMAP platform and Shaheen supercomputer. Why it matters: The findings confirm the role of macroalgae in carbon sequestration, highlighting their importance in blue carbon assessments for climate change mitigation and underscoring KAUST's contribution to environmental sustainability research.

A “divide-and-conquer” approach to learning from demonstration

MBZUAI ·

MBZUAI researchers have developed a "divide-and-conquer" technique to improve learning from demonstration in robotics. The approach breaks down complex dynamical systems into independently solvable subsystems, modeled as linear parameter-varying systems. This method aims to simplify computations while maintaining stability and accurately capturing joint interactions for robots in complex environments. Why it matters: The research addresses a key challenge in robotics, potentially enabling more efficient and safer robot learning from human demonstrations.

Edama opens new waste recycling facility

KAUST ·

Edama Organic Solutions, a KAUST startup, has opened a new organic waste recycling facility in the KAUST Research and Technology Park. The facility is the first of its kind in Saudi Arabia to use technology for waste processing and desert agriculture solutions. It will recycle 100% of KAUST's food and green waste, producing about 4,500 m3 of soil improver. Why it matters: This supports Saudi Vision 2030 by addressing environmental pollution and promoting sustainable agriculture in arid regions, aligning with the Saudi Green Initiative.

Bring Your Own Kernel! Constructing High-Performance Data Management Systems from Components

MBZUAI ·

Holger Pirk from Imperial College London is developing a novel approach to data management system composition called BOSS. The system uses a homoiconic representation of data and code and partial evaluation of queries by components, drawing inspiration from compiler-construction research. BOSS achieves a fully composable design that effectively combines different data models, hardware platforms, and processing engines, enabling features like GPU acceleration and generative data cleaning with minimal overhead. Why it matters: This research on composable database systems can broaden the applicability of data management techniques in the GCC region, enabling more flexible and efficient data processing for various applications.