Shai Gilgeous-Alexander and the Thunder face the LA Clippers in the second half of our ‘NBA Coast 2 Coast’ doubleheader on NBC and Peacock.
Enjoy the best of Tuesday’s six-game slate with the NBA.com live blog, featuring all of the…
Solar geoengineering could increase the ferocity of North Atlantic hurricanes, cause the Amazon rainforest to die back and cause drought in parts of Africa if deployed above only some parts of the planet by rogue actors, a report has warned.
Instead of disposing of it in landfills, food waste can be converted into energy and compost through proper treatment and processing. Two plants in Hong Kong are doing just that.
—
Managing food waste in Hong Kong is challenging. Currently, the recycling rate of food waste is low, and most of it is disposed of in landfills – which, however, are reaching their full capacities. What’s more, landfill operations have significant environmental impacts. For example, landfill gas, which primarily consists of methane and carbon dioxide, is a major contributor to global warming and poses a risk of gas explosions. Moreover, landfill leachate can contaminate groundwater and soil when liquids percolate through the solid waste.
In 2023, more than one million tonnes of food waste – approximately 3,200 tonnes per day – were disposed of in Hong Kong’s landfills, accounting for 29% of the total municipal solid waste. 63% of the total was produced by domestic households and 37% came from commercial and industrial sectors.
Food waste is, in fact, organic and biodegradable – and there are more efficient ways of disposing of it. One is composting, and the other is converting it into energy.
Currently, Hong Kong has two food waste recycling facilities: the Organic Resources Recovery Centre Phase 1 (O·Park1) in Siu Ho Wan, North Lantau, and Phase 2 (O·Park2) in Sha Ling, North District. They can treat 200 tonnes and 300 tonnes of food waste per day, respectively.
The plants convert food waste into biogas – a renewable energy source that can replace fossil fuels like natural gas and crude oil – for electricity generation. The residues from the process can also be produced as compost for landscaping and agriculture use.
The waste-to-energy process is straightforward. First, the food waste undergoes pre-treatment, such as the addition of water and removal of impurities. Then, the treated food waste undergoes anaerobic digestion, a biochemical process where anaerobic bacteria break down organic matter in an environment without oxygen. This process has two end products: biogas and digestate. While biogas is useful for generating heat and electricity, the digestate can be further processed for composting.
Biogas can be used as a fuel in combined heat and power (CHP) units. After proper treatment, the gas can be combusted to turn the generator to produce electricity. The electricity supports the operation of the recycling facility and achieves self-sustaining operation. The surplus electricity is exported to the power grid.
It is estimated that O·Park1 and O·Park2 can support the electricity consumption of 3,000 and 5,000 households annually, respectively. At the same time, heat recovery devices are used to capture heat from the CHP system and support the facility’s heating demand.
The wet material left over from anaerobic digestion is called digestate. It can be turned into compost after dewatering and further degradation. The compost is rich in nutrients and able to improve soil fertility, making it suitable for planting.
O·Park1 hosts a rooftop farm, O·Farm, demonstrating the application of compost in agriculture. In each harvesting season, O·Park1 donates the harvested crops to food donation organizations or distributes the crops to the community through educational and public events.
Currently, the public can redeem 100 grams of the compost via an app or schedule a visit to O·Park1 and bring their own container to collect the free compost. Government departments, schools, and organizations can apply for free compost by submitting an application form to the EPD.
To increase food waste recycling rates in Hong Kong, the Environmental Protection Department (EPD) has been installing food waste recycling bins in public rental housing estates, private housing estates, and various recycling stations.
In 2020, it implemented the GREEN$ Electronic Participation Incentive Scheme. The public can download a mobile app and earn points by recycling waste at the EPD’s recycling facilities. The points can be redeemed for gifts like daily necessities, or can be used for shopping at supermarkets and retail stores. Residents can earn a maximum of 50 points per day for recycling food waste.
Recent research by the Hong Kong University of Science and Technology suggests that since late 2023, public housing achieved complete coverage with smart bins, while collection points saw an 81% jump, and private housing bins surged by 230%. This push led to household recycling increasing fivefold, alongside a 50% increase in the volume of daily food waste collected.
As announced in the Chief Executive’s 2025 Policy Address, unveiled in September, the government is planning to keep expanding the food waste recycling network in residential areas, aiming at having at least one food waste recycling bin in each block of public rental housing estates by 2026. But the same research suggests that the goal has yet to be met, with private estates lagging significantly “due to complex application procedures.”
The EPD has also been providing free food waste collection services for commercial and industrial sectors since 2021. Premises producing a large amount of food waste, such as shopping malls and food factories, can contact the EPD to apply for food waste recycling bins. The EPD will arrange designated trucks to collect food waste on a daily basis. The department has also set up food waste recycling points at over 100 public refuse collection points and various temporary food waste recycling spots at fixed hours and locations every night.
The collected food waste is sent to O·Park1 and O·Park2 to be turned into biogas through a process known as for anaerobic digestion. The biogas is then used to generate electricity.
To further enhance Hong Kong’s food waste treatment capacity, the EPD has collaborated with the Drainage Services Department (DSD) to implement the Food Waste/Sludge Anaerobic Co-digestion Trial Scheme. Under the trial, which was implemented in 2019, a maximum of 50 tonnes of food waste per day is delivered to the sewage treatment plant for co-digestion with sewage sludge instead of being sent to landfills.
While the EPD handles the food waste pre-treatment and transportation processes, the DSD manages the co-digestion and energy recovery processes. The biogas generated for electricity generation is used to power the sewage treatment facilities’ internal power combustion, according to the scheme’s website.
Currently, co-digestion operations take place in Tai Po Sewage Treatment Works and Sha Tin Sewage Treatment Works.
While food waste recycling can transform waste into energy and compost, it is not a perfect long-term solution. Although the food waste recycling rate in Hong Kong has increased from 2% in 2018 to 6% in 2022, it remains very low. The root problem cannot be solved until households and business sectors change their habits and continue to create and dispose of food waste in rubbish bins. Complementary management strategies such as reducing food waste at the source and promoting food donations should thus also be part of the solution.
To reduce food waste at the source, the EPD suggests checking home food stocks to avoid over-purchasing, paying attention to expiration dates, properly storing food to prevent spoilage, and cooking or ordering a reasonable amount of food to minimize leftovers.
At the same time, businesses such as restaurants and canteens can consider donating surplus food when the hygiene conditions allow. Currently, Hong Kong has 17 charitable organizations that provide food donation services. They collect the surplus food, ensure food safety and quality, prepare meals, and redistribute them to people in need.
Featured image: Wikimedia Commons.
More on the topic: 11 Effective Solutions for Food Waste
Our non-profit newsroom provides climate coverage free of charge and advertising. Your one-off or monthly donations play a crucial role in supporting our operations, expanding our reach, and maintaining our editorial independence.
About EO | Mission Statement | Impact & Reach | Write for us
In a world of interconnected financial markets, policymakers and regulators face the complex task of identifying and addressing risks before they escalate into crises. The 2008-09 global crisis and recent episodes of market dysfunction highlight the need for early warning tools to detect vulnerabilities in real time. However, predicting financial market stress remains challenging, as traditional econometric models often fail to capture the complex, nonlinear dynamics and interconnectedness of modern financial systems.
Recent advances in artificial intelligence (AI) provide new tools to address these challenges. AI methods excel at analysing high-dimensional datasets and uncovering hidden patterns. While they are widely applied in asset pricing (Kelly et al. 2024), they are increasingly used for financial stability monitoring (Fouliard et al. 2021, du Plessis and Fritsche 2025). However, the ‘black box’ nature of AI models has limited their ability to generate actionable policy insights.
This article highlights recent research (Aldasoro et al. 2025, Aquilina et al. 2025) that advances the deployment of AI tools to anticipate financial market stress. These studies demonstrate the potential of AI to forecast market stress and dysfunction, offering both methodological innovations and actionable insights for policymakers by addressing the black-box issue.
Financial market stress can take many forms, including liquidity shortages, price dislocations, and breakdowns in arbitrage relationships. Events such as the 1998 LTCM crisis, the 2008-09 global crisis, and the 2020 ‘dash for cash’ highlight the systemic risks posed by market dysfunction. These disruptions often begin in specific market segments, such as foreign exchange or money markets, but can quickly spread throughout the financial system, threatening its stability. Increasingly, stress has also shifted from traditional banks to non-bank financial intermediaries, reflecting the evolving nature of financial intermediation.
Traditional early warning systems, which were primarily designed to predict full-blown crises, have had mixed success. These models often suffer from high false positive rates and struggle to account for the nonlinear interactions and feedback loops that amplify shocks during periods of stress.
Machine learning (ML) offers a promising alternative, particularly for generating early warning signals. Unlike traditional models, ML algorithms can process vast datasets, identify complex relationships, and adapt to changing market conditions. The studies discussed here demonstrate the potential of these tools to anticipate market stress and provide policymakers with timely warnings.
Aldasoro et al. (2025) present a novel framework for predicting financial market stress using machine learning. The study begins by constructing market condition indicators (MCIs) for three key US markets critical to financial stability: Treasury, foreign exchange, and money markets. These indicators (illustrated in Figure 1) capture dislocations in liquidity, volatility, and arbitrage conditions.
Figure 1 Market condition indices for US Treasury, foreign exchange, and money markets
The paper employs random forest models, a popular tree-based machine learning algorithm, to forecast the full distribution of future market conditions. This approach uses multiple decision trees and averages their predictions, reducing the risk of overfitting. The results are noteworthy: random forest models outperform traditional time-series approaches, particularly in predicting tail risks over longer time horizons (up to 12 months). This is especially evident in forecasting foreign exchange market conditions (Figure 2).
Figure 2 Forecast accuracy of random forest and autoregressive models
To address the black-box issue, the study uses Shapley value analysis to explain the main factors driving market stress predictions. The analysis reveals that macroeconomic expectations and uncertainty, particularly around monetary policy, are significant contributors to market vulnerability. Liquidity conditions and the state of the global financial cycle also play critical roles. This approach not only improves predictive accuracy but also provides actionable insights for policymakers, enabling them to respond proactively to the build-up of vulnerabilities.
Aquilina et al. (2025) take a different approach by integrating numerical data with textual information using large language models (LLMs). The study focuses on deviations from triangular arbitrage parity (TAP) in the euro-yen currency pair, a key indicator of dysfunction in the foreign exchange market. By combining recurrent neural networks (RNNs) with LLMs, the authors develop a two-stage framework to forecast market stress and identify its underlying drivers.
The recurrent neural network detects periods of heightened triangular arbitrage parity deviations up to 60 working days in advance, effectively predicting market dysfunctions that may occur within a one-month window. Out-of-sample testing on 3.5 years of data demonstrates the model’s practical value. For example, the model identified elevated risks before the March 2023 banking turmoil, despite being trained only on data up to the end of 2020 (Figure 3). However, it did not predict the market anomaly caused by the onset of COVID-19, as the event’s origins were external to the financial system.
Figure 3 Predictive accuracy of market dysfunction episodes
To address the black-box challenge, Aquilina et al. (2025) develop a new architecture for recurrent neural network models that dynamically assigns weights to input variables. This allows the model to identify which indicators are most important for predicting future market conditions at any given time. These weights can then be fed into an LLM to search financial news and commentary for contextual information, helping to uncover potential triggers of market stress.
For instance, during the March 2023 banking turmoil, the model flagged elevated risks in euro liquidity and cross-currency arbitrage. Guided by these signals, the LLM identified news articles discussing tightening dollar funding conditions and rising geopolitical tensions. This targeted approach transforms opaque statistical forecasts into narrative explanations that policymakers can understand and act upon.
While much more research into these issues is needed, these approaches show the promise of leveraging AI tools for financial stability monitoring and analysis.
Overall, these approaches represent a significant step forward in leveraging AI to detect vulnerabilities in financial markets. By combining different methods, the studies offer novel tools for forecasting market stress and understanding its underlying drivers. However, these methods are not without limitations, such as the risk of overfitting and the need for substantial computational resources. Policymakers and regulators should invest in the necessary data and infrastructure to fully harness the potential of these tools.
Aldasoro, I, P Hördahl and S Zhu (2022), “Under pressure: market conditions and stress”, BIS Quarterly Review (19): 31–45.
Aldasoro, I, P Hördahl, A Schrimpf and X S Zhu (2025), “Predicting Financial Market Stress with Machine Learning”, BIS Working Papers No. 1250.
Aquilina, M, D Araujo, G Gelos, T Park and F Pérez-Cruz (2025), “Harnessing Artificial Intelligence for Monitoring Financial Markets”, BIS Working Papers No. 1291.
Du Plessis, E and U Fritsche (2025), “New forecasting methods for an old problem: Predicting 147 years of systemic financial crises”, Journal of Forecasting 44 (1): 3-40.
Fouliard, J, M Howell, H Rey and V Stavrakeva (2021), “Answering the queen: Machine learning and financial crises”, NBER Working Paper 28302.
Huang, W, A Ranaldo, A Schrimpf and F Somogyi (2025), “Constrained liquidity provision in currency markets”, Journal of Financial Economics 167: 104028.
Kelly, B, S Malamud and K Zhou (2024), “The Virtue of Complexity in Return Prediction”, Journal of Finance 79: 459-503.
Pasquariello, P (2014), “Financial Market Dislocations”, Review of Financial Studies 27(6): 1868–1914.
“Harry Potter” is coming to life in two major ways: HBO’s upcoming TV series and Audible’s narrated audiobooks of all seven of J.K. Rowling’s novels.
The HBO series is still more than a year away, but…
This request seems a bit unusual, so we need to confirm that you’re human. Please press and hold the button until it turns completely green. Thank you for your cooperation!
SAN FRANCISCO and SUZHOU, China, Nov. 4, 2025 /PRNewswire/ — Innovent Biologics, Inc. (“Innovent”) (HKEX: 01801), a world-class biopharmaceutical company that develops,…
A bunch of GM cars can’t access their in-vehicle app store anymore.
The change affects some 2017 through 2020 vehicles, GMAuthority reports. Apps that affected owners have downloaded won’t receive support, and…