Combining machine learning and remote sensing-integrated crop modeling for rice and soybean crop simulation.

Machine learning (ML) techniques offer a promising avenue for improving the integration of remote sensing data into mathematical crop models, thereby enhancing crop growth prediction accuracy. A critical variable for this integration is the leaf area index (LAI), which can be accurately assessed using proximal or remote sensing data based on plant canopies. This study aimed to (1) develop a machine learning-based method for estimating the LAI in rice and soybean crops using proximal sensing data and (2) evaluate the performance of a Remote Sensing-Integrated Crop Model (RSCM) when integrated with the ML algorithms. To achieve these objectives, we analyzed rice and soybean datasets to identify the most effective ML algorithms for modeling the relationship between LAI and vegetation indices derived from canopy reflectance measurements. Our analyses employed a variety of ML regression models, including ridge, lasso, support vector machine, random forest, and extra trees. Among these, the extra trees regression model demonstrated the best performance, achieving test scores of 0.86 and 0.89 for rice and soybean crops, respectively. This model closely replicated observed LAI values under different nitrogen treatments, achieving Nash-Sutcliffe efficiencies of 0.93 for rice and 0.97 for soybean. Our findings show that incorporating ML techniques into RSCM effectively captures seasonal LAI variations across diverse field management practices, offering significant potential for improving crop growth and productivity monitoring.

Construction of a new LED chamber to measure net ecosystem exchange in low vegetation and validation study in grain crops.

A vegetation canopy chamber system measures gas exchanges in the field between plants and the environment. Transparent closed chambers have generally been used to measure canopy fluxes in the field, depending on solar radiation as the light source for photosynthesis. However, measuring canopy fluxes in nature can be challenging due to fluctuations in solar radiation. Therefore, we constructed a novel transient-state closed-chamber system using light-emitting diodes (LEDs) as a light source to measure canopy-scale fluxes. The water-cooled chamber system used a 1600 Watt LED module to produce constant photosynthetically active radiation (PAR) and a CO2 gas analyzer for concentration measurements. We used the LED chamber system to measure barley and wheat gas exchanges in the field to quantify CO2 fluxes along a PAR gradient. This novel technology enables the determination of photosynthesis rates for various crops under diverse environmental conditions, in diverse ecosystems, and across long-term interannual changes, including those due to climate change.

Cell wall thickness has phylogenetically consistent effects on the photosynthetic nitrogen-use efficiency of terrestrial plants.

Leaf photosynthetic nitrogen-use efficiency (PNUE) diversified significantly among C3 species. To date, the morpho-physiological mechanisms and interrelationships shaping PNUE on an evolutionary time scale remain unclear. In this study, we assembled a comprehensive matrix of leaf morpho-anatomical and physiological traits for 679 C3 species, ranging from bryophytes to angiosperms, to comprehend the complexity of interrelationships underpinning PNUE variations. We discovered that leaf mass per area (LMA), mesophyll cell wall thickness (Tcwm ), Rubisco N allocation fraction (PR ), and mesophyll conductance (gm ) together explained 83% of PNUE variations, with PR and gm accounting for 65% of those variations. However, the PR effects were species-dependent on gm , meaning the contribution of PR on PNUE was substantially significant in high-gm species compared to low-gm species. Standard major axis (SMA) and path analyses revealed a weak correlation between PNUE and LMA (r2 = 0.1), while the SMA correlation for PNUE-Tcwm was robust (r2 = 0.61). PR was inversely related to Tcwm , paralleling the relationship between gm and Tcwm , resulting in the internal CO2 drawdown being only weakly proportional to Tcwm . The coordination of PR and gm in relation to Tcwm constrains PNUE during the course of evolution.

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.

Simulation of Wheat Productivity Using a Model Integrated With Proximal and Remotely Controlled Aerial Sensing Information.

A crop model incorporating proximal sensing images from a remote-controlled aerial system (RAS) can serve as an enhanced alternative for monitoring field-based geospatial crop productivity. This study aimed to investigate wheat productivity for different cultivars and various nitrogen application regimes and determine the best management practice scenario. We simulated spatiotemporal wheat growth and yield by integrating RAS-based sensing images with a crop-modeling system to achieve the study objective. We conducted field experiments and proximal sensing campaigns to acquire the ground truth data and RAS images of wheat growth conditions and yields. These experiments were performed at Gyeongsang National University (GNU), Jinju, South Gyeongsang province, Republic of Korea (ROK), in 2018 and 2019 and at Chonnam National University (CNU), Gwangju, ROK, in 2018. During the calibration at GNU in 2018, the wheat yields simulated by the modeling system were in agreement with the corresponding measured yields without significant differences (p = 0.27-0.91), according to two-sample t-tests. Furthermore, the yields simulated via this approach were in agreement with the measured yields at CNU in 2018 and at GNU in 2019 without significant differences (p = 0.28-0.86), as evidenced by two-sample t-tests; this proved the validity of the proposed modeling system. This system, when integrated with remotely sensed images, could also accurately reproduce the geospatial variations in wheat yield and growth variables. Given the results of this study, we believe that the proposed crop-modeling approach is applicable for the practical monitoring of wheat growth and productivity at the field level.

Geographical variations in gross primary production and evapotranspiration of paddy rice in the Korean Peninsula.

The quantification of canopy photosynthesis and evapotranspiration of crops (ETc) is essential to appreciate the effects of environmental changes on CO2 flux and water availability in agricultural ecosystems and crop productivity. This study simulated the canopy photosynthesis and ET processes of paddy rice (Oryza sativa) based on the development of physiological modules (i.e., gross primary production [GPP] and ETc) and their incorporation into the GRAMI-rice model that uses remote sensing data. We also projected spatiotemporal variations in the GPP, ET, yield, and biomass of paddy rice at maturity using the updated GRAMI-rice model combined with geostationary satellite images to identify the relationships of canopy photosynthesis and ETc with crop productivity. GPP and ET data for paddy rice were obtained from three KoFlux sites in South Korea in 2015 and 2016. Vegetation indices were acquired from the Geostationary Ocean Color Imager (GOCI) of the Communication Ocean and Meteorological Satellite (COMS) from 2012 to 2017 and integrated into GRAMI-rice. GPP and ETc estimates using GRAMI-rice were in close agreement with flux tower estimates with Nash-Sutcliffe efficiency ranges of 0.40-0.79 for GPP and 0.49-0.62 for ETc. Also, GRAMI-rice was reasonably well incorporated with the COMS GOCI imagery and reproduced spatiotemporal variations in the GPP and ET of rice in the Korean peninsula. The current study results demonstrate that the updated GRAMI-rice model with the canopy photosynthesis and ETc modules is capable of reproducing spatiotemporal variations in CO2 assimilation and ET of paddy rice at various geographical scales and for regions of interest that are observable by satellite sensors (e.g., inaccessible North Korea).

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.

Quantifying differences in water and carbon cycling between paddy and rainfed rice (Oryza sativa L.) by flux partitioning.

Agricultural crops play an important role in the global carbon and water cycle. Global climate change scenarios predict enhanced water scarcity and altered precipitation pattern in many parts of the world. Hence, a mechanistic understanding of water fluxes, productivity and water use efficiency of cultivated crops is of major importance, i.e. to adapt management practices. We compared water and carbon fluxes of paddy and rainfed rice by canopy scale gas exchange measurements, crop growth, daily evapotranspiration, transpiration and carbon flux modeling. Throughout a monsoon rice growing season, soil evaporation in paddy rice contributed strongly to evapotranspiration (96.6% to 43.3% from initial growth to fully developed canopy and amounted to 57.9% of total water losses over the growing seasons. Evaporation of rainfed rice was significantly lower (by 65% on average) particularly before canopy closure. Water use efficiency (WUE) was significantly higher in rainfed rice both from an agronomic (WUEagro, i.e. grain yield per evapotranspiration) and ecosystem (WUEeco, i.e. gross primary production per evapotranspiration) perspective. However, our results also show that higher WUE in rainfed rice comes at the expense of higher respiration losses compared to paddy rice (26% higher on average). Hence, suggestions on water management depend on the regional water availability (i.e. Mediterranean vs. Monsoon climate) and the balance between higher respiratory losses versus a potential reduction in CH4 and other greenhouse gas emissions. Our results suggest that a shift from rainfed/unsaturated soil to waterlogged paddy conditions after closure of the rice canopy might be a good compromise towards a sustainable use of water while preserving grain yield, particularly for water-limited production areas.

Soil water availability and capacity of nitrogen accumulation influence variations of intrinsic water use efficiency in rice.

Leaf intrinsic water use efficiency (WUEi) coupling maximum assimilation rate (Amax) and transpirable water lost via stomatal conductance (gsc) has been gaining increasing concern in sustainable crop production. Factors that influence leaf Amax and WUEi in rice (Oryza sativa L. cv Unkang) at flooding and rainfed conditions were evaluated. Positive correlations for leaf nitrogen content (Nm) and maximum carboxylation rate (Vcmax), for nitrogen allocation in Rubisco enzymes and mesophyll conductance (gm) were evident independent of cropping cultures. Rainfed rice exhibited enriched canopy leaf average Nm resulting in higher Amax, partially supporting improved leaf WUEi. Maximum WUEi (up to 0.14 µmol mmol(-1)) recorded in rainfed rice under drought conditions resulted from increasing gm/gsc ratio while at cost of significant decline in Amax due to hydraulically constrained gsc. Amax sensitivity related to gsc which was regulated by plant hydraulic conductance. WUEi was tightly correlated to Vcmax/gsc and gm/gsc ratios across the paddy and rainfed not to light environment, morphological and physiological traits, highlighting enhance capacity of Nm accumulation in rainfed rice with gsc at moderately high level similar to paddy rice facilitate optimization in Amax and WUEi while, is challenged by drought-vulnerable plant hydraulic conductance.

Impacts of climate change on paddy rice yield in a temperate climate.

The crop simulation model is a suitable tool for evaluating the potential impacts of climate change on crop production and on the environment. This study investigates the effects of climate change on paddy rice production in the temperate climate regions under the East Asian monsoon system using the CERES-Rice 4.0 crop simulation model. This model was first calibrated and validated for crop production under elevated CO2 and various temperature conditions. Data were obtained from experiments performed using a temperature gradient field chamber (TGFC) with a CO2 enrichment system installed at Chonnam National University in Gwangju, Korea in 2009 and 2010. Based on the empirical calibration and validation, the model was applied to deliver a simulated forecast of paddy rice production for the region, as well as for the other Japonica rice growing regions in East Asia, projecting for years 2050 and 2100. In these climate change projection simulations in Gwangju, Korea, the yield increases (+12.6 and + 22.0%) due to CO2 elevation were adjusted according to temperature increases showing variation dependent upon the cultivars, which resulted in significant yield decreases (-22.1% and -35.0%). The projected yields were determined to increase as latitude increases due to reduced temperature effects, showing the highest increase for any of the study locations (+24%) in Harbin, China. It appears that the potential negative impact on crop production may be mediated by appropriate cultivar selection and cultivation changes such as alteration of the planting date. Results reported in this study using the CERES-Rice 4.0 model demonstrate the promising potential for its further application in simulating the impacts of climate change on rice production from a local to a regional scale under the monsoon climate system.