Whispering gallery mode (WGM) microresonators offer significant potential for precise displacement measurement owing to their compact size, ultrahigh sensitivity, and rapid response. However, conventional WGM displacement sensors are prone to noise interference, resulting in accuracy loss, while the demodulation process for displacement often exhibits prolonged duration. To address these limitations, this study proposes a rapid and high-precision displacement sensing method based on the dip areas of multiple resonant modes in a surface nanoscale axial photonics microresonator. By employing a neural network to fit the nonlinear relationship between displacement and the areas of multiple resonant dips, we achieve displacement prediction with an accuracy better than 0.03 µm over a range of 200 µm. In comparison to alternative sensing approaches, this method exhibits resilience to temperature variations, and its sensing performance remains comparable to that in a noise-free environment as long as the signal-to-noise ratio is greater than 25 dB. Furthermore, the extraction of the dip area enables significantly enhanced speed in displacement measurement, providing an effective solution for achieving rapid and highly accurate displacement sensing.