#科技头条# 【人工智能告诉你美国究竟有多少太阳能装置】

#科技头条# 【人工智能告诉你美国究竟有多少太阳能装置】近日,斯坦福大学研究人员通过DeepSolar神经网络分析了全美卫星图像,以计算美国的太阳能装置 ,并且发现比任何人想象的要多得多——美国48个州中至少有147万个不同大小的太阳能装置,从家庭屋顶板到公用事业所有的太阳能发电厂。据悉,这是由土木与环境工程副教授Ram Rajagopal和机械工程教授Arun Majumdar领导的研究人员对DeepSolar进行了一系列370,000幅卫星图像培训,每幅图像覆盖面积约9平方米(100平方英尺)的区域,通过指出哪些包括太阳能电池板。然后,机器学习计划找出了如何识别太阳能电池板,在93%的时间内正确发现它们。当它出错时,它往往会使装置数量不足,大约减少了10%。
该项研究的交互网址:http://web.stanford.edu/group/deepsolar/home

Forget Cats, This Neural Network Spots Solar Panels

Stanford's DeepSolar neural network analyzed satellite images to count U.S. solar installations—and there are a lot more than anybody thought

There are at least 1.47 million solar installations of varying sizes in the 48 contiguous U.S. states, from home rooftop panels to utility-owned solar power plants.

That’s the conclusion of DeepSolar, a machine learning algorithm developed by researchers at Stanford University that searches satellite images for solar panels. The count is higher than some previous estimates, like the OpenPVproject’s count of 1.02 million installations.

The researchers, led by Ram Rajagopal, associate professor of civil and environmental engineering, and Arun Majumdar, professor of mechanical engineering, trained DeepSolar on a set of 370,000 satellite images, each covering a region measuring approximately 9 square meters (100 square feet), by indicating which ones included solar panels. The machine learning program then figured out how to identify solar panels, spotting them correctly 93 percent of the time. When it erred, it tended to undercount the installations, missing about 10 percent.

Processing the full set of a billion images took about a month. For efficiency, the system did not review the most sparsely populated areas of the United States, which the researchers estimate would add about 5 percent to the overall count. The researchers plan to add those regions to future runs of the program, and also aim to calculate the angle and orientation of the panels to more accurately estimate power generation.

As part of this analysis, the researchers created a database of the solar installations and added in U.S. census data. They found that low and medium income households do not often install solar systems even when located in areas with high electric bills and lots of sunshine. They also discovered that there is a solar radiation threshold—4.5 kWh/m2/day—that triggers solar adoption, although income levels can affect that. Using this data, DeepSolar can now predict solar deployment density for a particular area.

The researchers released their results today to coincide with the publication of a paper in JouleMore information along with the raw data and an interactive map is available here. They plan to update the count annually.


Comments are closed.



无觅相关文章插件