资源环境科技发展态势分析平台

Enhanced silicate rock weathering (ERW), deployable with croplands, has potential use for atmospheric carbon dioxide (CO2) removal (CDR), which is now necessary to mitigate anthropogenic climate change(1). ERW also has possible co-benefits for improved food and soil security, and reduced ocean acidification(2-4). Here we use an integrated performance modelling approach to make an initial techno-economic assessment for 2050, quantifying how CDR potential and costs vary among nations in relation to business-as-usual energy policies and policies consistent with limiting future warming to 2 degrees Celsius(5). China, India, the USA and Brazil have great potential to help achieve average global CDR goals of 0.5 to 2gigatonnes of carbon dioxide (CO2) per year with extraction costs of approximately US$80-180 per tonne of CO2. These goals and costs are robust, regardless of future energy policies. Deployment within existing croplands offers opportunities to align agriculture and climate policy. However, success will depend upon overcoming political and social inertia to develop regulatory and incentive frameworks. We discuss the challenges and opportunities of ERW deployment, including the potential for excess industrial silicate materials (basalt mine overburden, concrete, and iron and steel slag) to obviate the need for new mining, as well as uncertainties in soil weathering rates and land-ocean transfer of weathered products.

A video-based deep learning algorithm-EchoNet-Dynamic-accurately identifies subtle changes in ejection fraction and classifies heart failure with reduced ejection fraction using information from multiple cardiac cycles.

Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease(1), screening for cardiotoxicity(2) and decisions regarding the clinical management of patients with a critical illness(3). However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training(4,5). Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.