基于小波神经网络的盲区重力数据预测

引入精度较高的小波神经网络预测局部盲区重力数据。通过实验，对比分析了不同地形数据分布状况下经度、纬度二维输入和经度、纬度、高程三维输入小波神经网络盲区重力数据预测精度，发现利用小波神经网络可以较好地实现高精度盲区重力数据的预测，同等地形条件下三维输入预测的数据精度更高，更有利于后期利用插值方法制备高精度重力基准图。同时，利用克里金法和小波神经网络对真实盲区进行预测。结果表明，两者的预测值相差不大，但小波神经网络的预测结果更为平滑，表明小波神经网络有良好的适应性。

The Gravity Data Forecast of Unmeasurable Zone Based on Wavelet Neural Network

In this paper, wavelet neural network is used to forecast the gravity data of the unmeasurable zone. In the experiment, the forecast precision of gravity data in different landforms is analyzed, contrasting two dimensional inputs with longitude and latitude, and three dimensional inputs with longitude, latitude and altitude. It is found that the use of wavelet neural network can achieve high forecast precision of gravity data in the unmeasurable zone, especially with three dimensional inputs. This is conducive to process the high-precision gravity reference map using interpolation methods.