Fatty acid abundance is a key parameter for evaluating the quality of edible oils. This study developed a rapid and non-destructive method for predicting palmitic acid content in edible oils by combining visible-near-infrared (Vis-NIR) reflectance spectroscopy with deep learning models. A total of 1740 reflectance spectra in the range of 350–2500 nm were collected from 87 brands of edible oils, including peanut, soybean, corn, sunflower, rapeseed, sesame, and olive oils. Reference values of palmitic acid content were determined via gas chromatography–mass spectrometry (GC-MS). Two conventional machine learning models (SVR and KNN) and four deep learning models (1D-CNN, 1D-ResNet, 1D-Inception, and 1D-Inception-ResNet) were developed and compared using both full-spectrum data and CARS selected characteristic wavelengths. Among the full-spectrum models, the designed 1D-ResNet model achieved the best performance, with the determination coefficient of prediction ($R_p^2$) of 0.9027 and the root mean square error of prediction ($RMS{E}_p$) of 1.13 in the prediction dataset. The proposed 1D-Inception-ResNet model yielded the best prediction results based on the 91 selected informative wavelengths via competitive adaptive reweighted sampling (CARS), achieving an $R_p^2$ of 0.9825 and an $RMS{E}_p$ of 0.4804 in the prediction dataset. The experimental results indicated that Vis-NIR reflectance spectroscopy combined with informative wavelength selection and deep learning models provided an effective strategy for rapid prediction of palmitic acid content in edible oils.

Early-season winter wheat mapping is crucial for agricultural management and food security, but reliable identification remains challenging under weak spectral conditions during early growth stages. To address this challenge, this study developed a CNN–LSTM with a lag-aware gated fusion model (CL-LGFM) for winter wheat mapping in the Chaohu Basin, China, using a reconstructed 5-day Sentinel-2 NDVI time series and precipitation data from the Global Precipitation Measurement (GPM) mission. The model employs a dual-branch architecture to jointly learn vegetation and precipitation features and introduces a lag-aware dynamic gated fusion module to capture the delayed response of vegetation to precipitation and enhance multi-source feature fusion. The results show that the proposed method achieved reliable early-season winter wheat mapping (OA ≥ 0.90, Kappa ≥ 0.80) on 26 January, at least 10 days earlier than traditional methods, including SVM, RF, DTW, and TCN, using the same reconstructed 5-day NDVI time series. Optimal performance uses a 7 × 7 patch size and 30-day precipitation window.