The leaf area index (LAI) is an essential indicator used in crop growth monitoring. In the study, a hybrid inversion method, which combined a physical model with a statistical method, was proposed to estimate the crop LAI. The simulated compact high-resolution imaging spectrometer (CHRIS) canopy spectral crop reflectance datasets were generated using the PROSAIL model (the coupling of PROSPECT leaf optical properties model and Scattering by Arbitrarily Inclined Leaves model) and the CHRIS band response function. Partial least squares (PLS) was then used to reduce the dimension of the simulated spectral data. Using the principal components (PCs) of PLS as the model inputs, the hybrid inversion models were built using various modeling algorithms, including the backpropagation artificial neural network (BP-ANN), least squares support vector regression (LS-SVR), and random forest regression (RFR). Finally, remote sensing mapping of the CHRIS data was achieved with the hybrid model to test the inversion accuracy of LAI estimates. The validation result yielded an accuracy of R² = 0.939 and normalized root-mean-square error (NRMSE) = 6.474% for the PLS_RFR model, which indicated that the crops LAI could be estimated accurately by using spectral feature extraction and a hybrid inversion strategy. The results showed that the model based on principal components extracted by PLS had a good estimation accuracy and noise immunity and was the preferred method for LAI estimation. Furthermore, the comparative analysis results of various datasets showed that prior knowledge could improve the precision of the retrieved LAI, and using this information to constrain parameters (e.g., chlorophyll content or LAI), which make important contributions to the spectra, is the key to this improvement. In addition, among the PLS, BP-ANN, LS-SVR, and RFR methods, RFR was the optimal modeling algorithm in the paper, as indicated by the high R² and low NRMSE in various datasets.

Soil salinisation is a global problem that hinders the sustainable development of ecosystems and agricultural production. Remote and proximal sensing technologies have been used to effectively evaluate soil salinity over large scales, but research on digital camera images is still lacking. In this study, we propose to relate the pixel brightness of soil surface digital images to the soil salinity information. We photographed the surface of 93 soils in the field at different times and weather conditions, and sampled the corresponding soils for laboratory analyses of soil salinity information. Results showed that the pixel digital numbers were related to soil salinity, especially at the intermediate and higher brightness levels. Based on this relationship, we employed random forest (RF) and partial least-squares regression (PLSR) to model soil salt content and ion concentrations, and applied root mean squared error, coefficient of determination and Lin’s concordance correlation coefficient to evaluate the accuracy of models. We found that ions with high concentration were estimated more accurately than ions with low concentrations, and RF models performed overall better than PLSR models. However, the method is only suitable for bare land of coastal soil, and verification is needed for other conditions. In conclusion, a new approach of using digital camera images has good potential to predict and manage soil salinity in the context of precision agriculture with the rapid development of unmanned aerial vehicles.

Soil roughness is important for characterizing soil surface, and plays an important role in many land surface models. Previous studies have proposed many methods to describe and model soil roughness. In this study, we use a simple way to measure soil surface roughness and try to find a simpler method to estimate it. We measure soil roughness in a ploughed farmland with an inelastic soft rope as an invention patent says, and then capture the photographs corresponding to the measured field points. Our philosophy is that soil roughness causes the shadows in the photo, so the shadows can be used to invert soil roughness. First, we binarize digital images to calculate the shadow area ratio in each photo. Different shadow area ratios will be obtained with different binarization threshold values, and here we use 6 threshold values to get 6 shadow area ratios. Then we try to use the 6 variables to model soil roughness with random forest method. We divide the dataset to two categories: training data (70%) for modeling and testing data (30%) for validation. We repeat the modeling process for 100 times to get the best model. The model shows a relatively satisfied result with a R2 of 0.81, and a RMSE of 0.05. We conclude that it is a viable way to estimate soil roughness with digital photos. The findings provide a simple and fast means for maximize the potential of digital cameras in estimating soil attributes in the field scales.