Integration of APSIM and PROSAIL models to develop more precise radiometric estimation of crop traits using deep learning

Abstract

A major challenge for the estimation of crop traits (biophysical variables) from canopy reflectance is the creation of a high-quality training dataset. This can be addressed by using radiative transfer models (RTMs) to generate training dataset representing "real-world" data in situations with varying crop types and growth status as well as various observation configurations. However, this approach can lead to "ill-posed" problems related to assumptions in the sampling strategy and due to uncertainty in the model, resulting in unsatisfactory inversion results for retrieval of target variables. In order to address this problem, this research investigates a practical way to generate higher quality "synthetic" training data by integrating a crop growth model (CGM, in this case APSIM) with an RTM (in this case PROSAIL). This allows control of uncertainties of the RTM by imposing biological constraints on distribution and co-distribution of related variables. Subsequently, the method was theoretically validated on two types of synthetic dataset generated by PROSAIL or the coupling of APSIM and PROSAIL through comparing estimation precision for leaf area index (LAI), leaf chlorophyll content (Cab), leaf dry matter (Cm) and leaf water content (Cw). Additionally, the capabilities of current deep learning techniques using high spectral resolution hyperspectral data were investigated. The main findings include: (1) Feedforward neural network (FFNN) provided with appropriate configuration is a promising technique to retrieve crop traits from input features consisting of 1 nm-wide hyperspectral bands across 400-2500 nm range and observation configuration (solar and viewing angles), leading to a precise joint estimation for LAI (RMSE=0.061 m2 m-2), Cab (RMSE=1.42 μg cm-2), Cm (RMSE=0.000176 g cm-2) and Cw (RMSE=0.000319 g cm-2); (2) For the aim of model simplification, a narrower range in 400-1100 nm without observation configuration in input of FFNN model provided less precise estimation for LAI (RMSE=0.087 m2 m-2), Cab (RMSE=1.92 μg cm-2), Cm (RMSE=0.000299 g cm-2) and Cw (RMSE=0.001271 g cm-2); (3) The introduction of biological constraints in training datasets improved FFNN model performance in both average precision and stability, resulting in a much accurate estimation for LAI (RMSE=0.006 m2 m-2), Cab (RMSE=0.45 μg cm-2), Cm (RMSE=0.000039 g cm-2) and Cw (RMSE=0.000072 g cm-2), and this improvement could be further increased by enriching sample diversity in training dataset.

A Review of Hybrid Approaches for Quantitative Assessment of Crop Traits Using Optical Remote Sensing: Research Trends and Future Directions

“…Another remark is that after ANN, GPR is becoming more popular and applicable in the retrieval process, since Verrelst et al [130] found that GPR had the best performance using Sentinel-2 and -3 and provides retrieval uncertainties (Figure 7). Nowadays, deep learning (DL), as extending machine learning, is starting to be explored for crop monitoring using hyperspectral images [34,229]. DL has the advantage of handling a large data size of training samples to possibly improve the targeted variable.…”

“…Ultimately, the success of NN performance relies on how the user adjusts the hyperparameters, such as the number of hidden layers and neurons in the layer, to minimize the difference between the model prediction and the desired outcome, respecting a good trade-off between the computational time, stability, and accuracy [34].…”

“…Indeed, the terminology of a hybrid approach is widely denominated when combining at least two methods, as claimed in the study of [32]. For instance, the hybrid method can be a combination of a crop growth model (CGM) with a canopy RTM [33,34], a geometric and a turbid medium model to represent the canopy in three-dimensional (3D) space RTM [35], a geostatistical method with machine learning (ML) [36], or blending two methods of MLs [37]. Verrelst et al [18] and Berger et al [32] exemplified the conceptual framework of retrieval strategies, including the hybrid method based on a combination of RTMs with MLs for estimating vegetation traits.…”