Pedogenic-weathering evolution and soil discrimination by sensor fusion combined with machine-learning-based spectral modeling

•3D spectral model developed to fingerprint loess soils using principal component analysis.•Sensor fusion improves the performance of machine-learning-based models.•Spectral modeling provides alternative to mineral/geochemical pedogenic proxies.•Loess deposits from various climatic zones were influenced by the Asian monsoons.•Spectral modeling facilitates large-scale investigation of environmental changes.