Incorporation of machine learning and deep neural network approaches into a remote sensing-integrated crop model for the simulation of rice growth.

Machine learning (ML) and deep neural network (DNN) techniques are promising tools. These can advance mathematical crop modelling methodologies that can integrate these schemes into a process-based crop model capable of reproducing or simulating crop growth. In this study, an innovative hybrid approach for estimating the leaf area index (LAI) of paddy rice using climate data was developed using ML and DNN regression methodologies. First, we investigated suitable ML regressors to explore the LAI estimation of rice based on the relationship between the LAI and three climate factors in two administrative rice-growing regions of South Korea. We found that of the 10 ML regressors explored, the random forest regressor was the most effective LAI estimator, and it even outperformed the DNN regressor, with model efficiencies of 0.88 in Cheorwon and 0.82 in Paju. In addition, we demonstrated that it would be feasible to simulate the LAI using climate factors based on the integration of the ML and DNN regressors in a process-based crop model. Therefore, we assume that the advancements presented in this study can enhance crop growth and productivity monitoring practices by incorporating a crop model with ML and DNN plans.

Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea.

Prediction of rice yields at pixel scale rather than county scale can benefit crop management and scientific understanding because it is useful for monitoring how crop yields respond to various agricultural systems and environmental factors. In this study, we propose a methodology for the early prediction of rice yield at pixel scale combining a crop model and a deep learning model for different agricultural systems throughout South and North Korea. Initially, satellite-integrated crop models were applied to obtain a pixel-scale reference rice yield. Then, the pixel-scale reference rice yields were used as target labels in the deep learning model to leverage the advantages of crop models. Models of five different deep learning network architectures were employed to help determine the hybrid structure of long-short term memory (LSTM) and one-dimensional convolutional neural network (1D-CNN) layers by predicting the optimal model about two months ahead of harvest time. The suggested model showed good performance [R2 = 0.859, Nash-Sutcliffe model efficiency = 0.858, root mean squared error = 0.605 Mg ha-1], with specific spatial patterns of rice yields for South and North Korea. Analysis of the relative importance of the input variables showed the water-related index and maximum temperature in North Korea and the vegetation indices and geographic variables in South Korea to be crucial for predicting rice yields. The proposed approach successfully predicted and diagnosed rice yield at the pixel scale for inaccessible locations where reliable ground measurements are not available, especially North Korea.

Spatial Assessment of Solar Radiation by Machine Learning and Deep Neural Network Models Using Data Provided by the COMS MI Geostationary Satellite: A Case Study in South Korea.

Although data-driven methods including deep neural network (DNN) were introduced, there was not enough assessment about spatial characteristics when using limited ground observation as reference. This work aimed to interpret the feasibility of several machine learning approaches to assess the spatial distribution of solar radiation on Earth based on the Communication, Ocean, and Meteorological Satellite (COMS) Meteorological Imager (MI) geostationary satellite. Four data-driven models were selected (artificial neural network (ANN), random forest (RF), support vector regression (SVR), and DNN), to compare their accuracy and spatial estimating performance. Moreover, we used a physical model to probe the ability of data-driven methods, implementing hold-out and k-fold cross-validation approaches based on pyranometers located in South Korea. The results of analysis showed the RF had the highest accuracy in predicting performance, although the difference between RF and the second-best technique (DNN) was insignificant. Temporal variations in root mean square error (RMSE) were dependent on the number of data samples, while the physical model showed relatively less sensitivity. Nevertheless, DNN and RF showed less variability in RMSE than the others. To examine spatial estimation performance, we mapped solar radiation over South Korea for each model. The data-driven models accurately simulated the observed cloud pattern spatially, whereas the physical model failed to do because of cloud mask errors. These exhibited different spatial retrieval performances according to their own training approaches. Overall analysis showed that deeper layers of networks approaches (RF and DNN), could best simulate the challenging spatial pattern of thin clouds when using satellite multispectral data.

Monitoring paddy productivity in North Korea employing geostationary satellite images integrated with GRAMI-rice model.

To meet the growing demands of staple crops with a strategy to develop amicable strategic measures that support efficient North Korean relief policies, it is a desirable task to accurately simulate the yield of paddy (Oryza sativa), an important Asian food commodity. We aim to address this with a grid-based crop simulation model integrated with satellite imagery that enables us to monitor the crop productivity of North Korea. Vegetation Indices (VIs), solar insolation, and air temperature data are thus obtained from the Communication Ocean and Meteorological Satellite (COMS), including the reanalysis data of the Korea Local Analysis and Prediction System (KLAPS). Paddy productivities for North Korea are projected based on the bidirectional reflectance distribution function-adjusted VIs and the solar insolation using the grid GRAMI-rice model. The model is calibrated on a 500-m grid paddy field in Cheorwon, and the model simulation performance accuracy is verified for Cheorwon and Paju, located at the borders of North Korea using four years of data from 2011 to 2014. Our results show that the paddy yields are reproduced reasonably accurately within a statistically significant range of accuracy, in comparison with observation data in Cheorwon (p = 0.183), Paju (p = 0.075), and NK (p = 0.101) according to a statistical t-test procedure. We advocate that incorporating a crop model with satellite images for crop yield simulations can be utilised as a reliable estimation technique for the monitoring of crop productivity, particularly in unapproachable, data-sparse regions not only in North Korea, but globally, where estimations of paddy productivity can assist in planning of agricultural activities that support regionally amicable food security strategies.