摘要
本文提出一种用神经网络确定测区似大地水准面的方法，并给出了相应的神经网络结构和算法。研究了一个测区中用该方法确定的似大地水准面的精度，结果表明用该方法确定的似大地水准面的精度为厘米级，并与二次多项式曲面拟合似大地水准面的方法作了比较，神经网络方法的精度较优。
In this paper a method for determination of quasi Geoid in survey zone using artificial neural network is proposed, a architecture and algorithm of neural networks are also given. The accuracy of quasi geoid determined by this method is investigated in a survey area, the results show that the accuracy is about the order of 3cm, it is compared with method of fitting quasi geoid using quadric polynomial, and it is better.
出处
《四川测绘》
1999年第1期14-20,共7页
Surveying and Mapping of Sichuan
