• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1031-1042
• /
• 2023

In this study, a deep learning model was developed to predict the yield of cabbage and radish, one of the five major supply and demand management vegetables, using satellite images of Landsat 8. To predict the yield of cabbage and radish in Gangwon-do from 2015 to 2020, satellite images from June to September, the growing period of cabbage and radish, were used. Normalized difference vegetation index, enhanced vegetation index, lead area index, and land surface temperature were employed in this study as input data for the yield model. Crop yields can be effectively predicted using satellite images because satellites collect continuous spatiotemporal data on the global environment. Based on the model developed previous study, a model designed for input data was proposed in this study. Using time series satellite images, convolutional neural network, a deep learning model, was used to predict crop yield. Landsat 8 provides images every 16 days, but it is difficult to acquire images especially in summer due to the influence of weather such as clouds. As a result, yield prediction was conducted by splitting June to July into one part and August to September into two. Yield prediction was performed using a machine learning approach and reference models , and modeling performance was compared. The model's performance and early predictability were assessed using year-by-year cross-validation and early prediction. The findings of this study could be applied as basic studies to predict the yield of field crops in Korea.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.1
• /
• pp.47-56
• /
• 2018

Providing high-quality meteorological observation data at sites that represent actual farming environments is essential for useful agrometeorological services. The Automated Agricultural Observing System (AAOS) of the Korean Meteorological Administration, however, has been deployed on lawns rather than actual farm land. In this study, we show the inaccuracies that arise in AAOS data by analyzing temporal and vertical variation and by comparing them with data recorded by the National Center for AgroMeteorology (NCAM) tower that is located at an actual farming site near the AAOS tower. The analyzed data were gathered in August and October (before and after harvest time, respectively). Observed air temperature and water vapor pressure were lower at AAOS than at NCAM tower before and after harvest time. Observed reflected shortwave radiation tended to be higher at AAOS than at NCAM tower. Soil variables showed bigger differences than meteorological observation variables. In August, observed soil temperature was lower at NCAM tower than at AAOS with smaller diurnal changes due to irrigation. The soil moisture observed at NCAM tower continuously maintained its saturation state, while the one at AAOS showed a decreasing trend, following an increase after rainfall. The trend changed in October. Observed soil temperature at NCAM showed similar daily means with higher diurnal changes than at AAOS. The soil moisture observed at NCAM was continuously higher, but both AAOS and NCAM showed similar trends. The above results indicate that the data gathered at the AAOS are inaccurate, and that ground surface cover and farming activities evoke considerable differences within the respective meteorological and soil environments. We propose to shift the equipment from lawn areas to actual farming sites such as rice paddies, farms and orchards, so that the gathered data are representative of the actual agrometeorological observations.

• Korean Journal of Remote Sensing
• /
• v.32 no.3
• /
• pp.221-234
• /
• 2016

In Korea, most industrial parks and major cities are located in coastal areas, which results in serious environmental problems in both coastal land and ocean. In order to effectively manage such problems especially in coastal ocean, water quality should be monitored. As there are many factors that influence water quality, the Korean Government proposed an integrated Water Quality Index (WQI) based on in situmeasurements of ocean parameters(bottom dissolved oxygen, chlorophyll-a concentration, secchi disk depth, dissolved inorganic nitrogen, and dissolved inorganic phosphorus) by ocean division identified based on their ecological characteristics. Field-measured WQI, however, does not provide spatial continuity over vast areas. Satellite remote sensing can be an alternative for identifying WQI for surface water. In this study, two schemes were examined to estimate coastal WQI around Korea peninsula using in situ measurements data and Geostationary Ocean Color Imager (GOCI) satellite imagery from 2011 to 2013 based on machine learning approaches. Scheme 1 calculates WQI using estimated water quality-related factors using GOCI reflectance data, and scheme 2 estimates WQI using GOCI band reflectance data and basic products(chlorophyll-a, suspended sediment, colored dissolved organic matter). Three machine learning approaches including Random Forest (RF), Support Vector Regression (SVR), and a modified regression tree(Cubist) were used. Results show that estimation of secchi disk depth produced the highest accuracy among the ocean parameters, and RF performed best regardless of water quality-related factors. However, the accuracy of WQI from scheme 1 was lower than that from scheme 2 due to the estimation errors inherent from water quality-related factors and the uncertainty of bottom dissolved oxygen. In overall, scheme 2 appears more appropriate for estimating WQI for surface water in coastal areas and chlorophyll-a concentration was identified the most contributing factor to the estimation of WQI.

• Journal of Korean Society of Forest Science
• /
• v.24 no.1
• /
• pp.1-24
• /
• 1974

A national programme of erosion control for soil and water conservation needs to be based on factual information about rates and quantities of soil erosion and of water runoff. The best and simplest way of reducing sedimentation pollution is to prevent or control the erosion at its sources. Steeply sloping earth banks are liable to both surface erosion and land-slides and the key to the control of these form of erosion lies with drainages and dense vegetation establishment including surface mulching on the slopes. Micro-plots having $1.6m^2$ (1 metre in width and 1.6 metres in slope length, and 1:1.2 in gradient) of banking slopes on the coarse sand soil are used to establish the order of magnititude of the difference in controlling of soil erosion and water runoff, and in potentiality of execution in consideration of the values of landscapes, performed on the 2 repetetions of six-experiment plots consisted of five surface mulches including seedings and one bare slope as a control treatment. The main results obtained may be summarized as follows: 1. The significant difference is realized in the quantities of soil erosion between the measures of six treatments. 2. Excepting the differences between treatment III and VI, the significant difference is realized in the rate of surface runoff between each treatment measures. 3. Both measures of treatment II and IV are recognized as the most effective measures in controlling the soil erosion and water runoff and also in establishing the ground vegetation. (Treatment II is a measures of the coarse straw-mat mulchings on the micro-strip seedings, Treatment IV is a measures of the "SPRAY-ON method" on the micro-strip seedings). In consideration of the potentiality of execution as well as the value of landscapes, the measures of treatment II could be recommendable for establishing the vegetation cover on the denuded gentle slopes in hillsides while the measures of treatment IV could be suitable for accelerating the establishment of vegetation on steeply sloping earth banks and cuts.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.2
• /
• pp.107-120
• /
• 2017

There are many wildfire risk indices worldwide, but objective comparisons between such various wildfire risk indices and surface dryness indices have not been conducted for the wildfire cases in Korea. This paper describes a sensitivity analysis on the wildfire risk indices and surface dryness indices for Korea using LDAPS(Local Analysis and Prediction System) meteorological dataset on a 1.5-km grid and MODIS(Moderate-resolution Imaging Spectroradiometer) satellite images on a 1-km grid. We analyzed the meteorology-based wildfire risk indices such as the Australian FFDI(forest fire danger index), the Canadian FFMC(fine fuel moisture code), the American HI(Haines index), and the academically presented MNI(modified Nesterov index). Also we examined the satellite-based surface dryness indices such as NDDI(normalized difference drought index) and TVDI(temperature vegetation dryness index). As a result of the comparisons between the six indices regarding 120 wildfire cases with the area damaged over 1ha during the period between January 2013 and May 2017, we found that the FFDI and FFMC showed a good predictability for most wildfire cases but the MNI and TVDI were not suitable for Korea. The NDDI can be used as a proxy parameter for wildfire risk because its average CDF(cumulative distribution function) scores were stably high irrespective of fire size. The indices tested in this paper should be carefully chosen and used in an integrated way so that they can contribute to wildfire forecasting in Korea.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.4 no.1
• /
• pp.38-48
• /
• 2002

This study examines the relationships between atmospheric influences and grain yields including yield components as well as growth stages. Data used in this study were collected from the long-term field experiment at Suwon for the period between 1974 and 2000. Mean grain yield of barley cultivar, Olbori, for the recent 14 years(1987∼2000) with warm winters was higher by 0.42 ton per hectare than that for 27 years(1974∼2000) at Suwon as a result of the higher numbers of spikes per unit land area and grains per spike. However, the 1000-grain weight decreased by about 0.6 gram. Mean first day of regrowth for the recent 14 years was earlier by five days than that for 27 years. Also, beginning date of regrowth was positively correlated with that of heading and ripening. Mean period of ripening for the years of 1987 through 2000 was similar to that for 27 years, but mean period of overwintering was shorter by nine days than that for 27 years. On the other hand, mean periods of seedling and tillering were longer by three days than those for 27 years. Meteorological elements at various growth stages affecting grain yield of winter barley were air temperature (positive correlation) and sunshine hour (negative correlation) of overwintering stage, precipitation (negative correlation) of tillering stage, and potential evapotranpiration (positive correlation) of tillering stage. The 1000-grain weight was not significantly correlated with the meteorological elements. Culm length was negatively influenced by high temperature and dry weather situations during the ripening period, but spike length was positively influenced. Overall, it was found that grain yield of barley, cultivar Olbori, was iufluenced by meteorological elements of overwintering, tillering, and ripening stages.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.3
• /
• pp.227-235
• /
• 2015

Using eddy covariance method, net ecosystem exchange (NEE) of $CO_2$ ($F_{CO_2}$), $H_2O$ (LE), and sensible heat (H) can be approximated as the sum of eddy flux ($F_c$) and storage flux term ($F_s$). Depending on strength and distribution of sink/source of scalars and magnitude of vertical turbulence mixing, the rates of changes in scalars are different with height. In order to calculate $F_s$ accurately, the differences should be considered using scalar profile measurement. However, most of flux sites for agricultural lands in Asia do not operate profile system and estimate $F_s$ using single-level scalars from eddy covariance system under the assumption that the rates of changes in scalars are constant regardless of the height. In this study, we measured $F_c$ and $F_s$ of $CO_2$, $H_2O$, and air temperature ($T_a$) using eddy covariance and profile system (i.e., the multi-level measurement system in scalars from eddy covariance measurement height to the land surface) at the Chengmicheon farmland site in Korea (CFK) in order to quantify the differences between $F_s$ calculated by single-level measurements ($F_s_{-single}$ i.e., $F_s$ from scalars measured by profile system only at eddy covariance system measurement height) and $F_s$ calculated by profile measurements and verify the errors of NEE caused by $F_s_{-single}$. The rate of change in $CO_2$, $H_2O$, and Ta were varied with height depending on the magnitudes and distribution of sink and source and the stability in the atmospheric boundary layer. Thus, $F_s_{-single}$ underestimated or overestimated $F_s$ (especially 21% underestimation in $F_s$ of $CO_2$ around sunrise and sunset (0430-0800 h and 1630-2000 h)). For $F_{CO_2}$, the errors in $F_s_{-single}$ generated 3% and 2% underestimation of $F_{CO_2}$ during nighttime (2030-0400 h) and around sunrise and sunset, respectively. In the process of nighttime correction and partitioning of $F_{CO_2}$, these differences would cause an underestimation in carbon balance at the rice paddy. In contrast, there were little differences at the errors in LE and H caused by the error in $F_s_{-single}$, irrespective of time.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.4
• /
• pp.317-326
• /
• 2019

Salinity which is often detected on reclaimed land is a major detrimental factor to crop growth. It would be advantageous to develop an approach for assessment of salinity and drought damages using a non-destructive method in a large landfills area. The objective of this study was to examine applicability of the decision tree classifier using imagery for classifying for spring potatoes (Solanum tuberosum) damaged by salinity or drought at vegetation growth stages. We focused on comparing the accuracies of OA (Overall accuracy) and KC (Kappa coefficient) between the simple reflectance and the band ratios minimizing the effect on the light unevenness. Spectral merging based on the commercial band width with full width at half maximum (FWHM) such as 10 nm, 25 nm, and 50 nm was also considered to invent the multispectral image sensor. In the case of the classification based on original simple reflectance with 5 nm of FWHM, the selected bands ranged from 3-13 bands with the accuracy of less than 66.7% of OA and 40.8% of KC in all FWHMs. The maximum values of OA and KC values were 78.7% and 57.7%, respectively, with 10 nm of FWHM to classify salinity and drought damages of spring potato. When the classifier was built based on the band ratios, the accuracy was more than 95% of OA and KC regardless of growth stages and FWHMs. If the multispectral image sensor is made with the six bands (the ratios of three bands) with 10 nm of FWHM, it is possible to classify the damaged spring potato by salinity or drought using the reflectance of images with 91.3% of OA and 85.0% of KC.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.2 no.2
• /
• pp.47-61
• /
• 2000

Agroclimatic zoning was done for paddy rice culture in North Korea based on a simulation experiment. Daily weather data for the experiment were generated by 3 steps consisting of spatial interpolation based on topoclimatological relationships, zonal summarization of grid cell values, and conversion of monthly climate data to daily weather data. Regression models for monthly climatological temperature estimation were derived from a statistical procedure using monthly averages of 51 standard weather stations in South and North Korea (1981-1994) and their spatial variables such as latitude, altitude, distance from the coast, sloping angle, and aspect-dependent field of view (openness). Selected models (0.4 to 1.6$^{\circ}C$ RMSE) were applied to the generation of monthly temperature surface over the entire North Korean territory on 1 km$\times$l km grid spacing. Monthly precipitation data were prepared by a procedure described in Yun (2000). Solar radiation data for 27 North Korean stations were reproduced by applying a relationship found in South Korea ([Solar Radiation, MJ m$^{-2}$ day$^{-1}$ ] =0.344 + 0.4756 [Extraterrestrial Solar Irradiance) + 0.0299 [Openness toward south, 0 - 255) - 1.307 [Cloud amount, 0 - 10) - 0.01 [Relative humidity, %), $r^2$=0.92, RMSE = 0.95 ). Monthly solar irradiance data of 27 points calculated from the reproduced data set were converted to 1 km$\times$1 km grid data by inverse distance weighted interpolation. The grid cell values of monthly temperature, solar radiation, and precipitation were summed up to represent corresponding county, which will serve as a land unit for the growth simulation. Finally, we randomly generated daily maximum and minimum temperature, solar irradiance and precipitation data for 30 years from the monthly climatic data for each county based on a statistical method suggested by Pickering et a1. (1994). CERES-rice, a rice growth simulation model, was tuned to accommodate agronomic characteristics of major North Korean cultivars based on observed phenological and yield data at two sites in South Korea during 1995~1998. Daily weather data were fed into the model to simulate the crop status at 183 counties in North Korea for 30 years. Results were analyzed with respect to spatial and temporal variation in yield and maturity, and used to score the suitability of the county for paddy rice culture.

• Journal of Korean Society of Forest Science
• /
• v.27 no.1
• /
• pp.5-14
• /
• 1975

Eroded sloping faces in hillsides including cut-bank slopes are liable to both surface erosion and land-slides and the key to control of these form of erosion lies with drainages of excessive run-off and dense vegetation establishment including surface mulching on the slopes. Micro-plots having $1.6m^2$ (1 metre in width and 1.6 metres in slope length, and 1:1.2 in gradient) of banking slopes on coarse sand soil are used to establish the order of magnititude of the difference in controlling of soil erosion and water runoff, and in rating of survival, performed on the repetetions of three-experiment plots consisted of such three levels as 90% (Dense), 70% (Moderate), and 50% Sparse of the density of the coarse straw-mat mulchings. The main results obtained may be summarized as follows: 1. The rates of surface runoff are calculated as 13.13% from the dense mulchings, 14.21% from the moderate mulchings, and 15.57% from the sparse mulchings respectively. 2. The total amounts of soil loss are measured as about 1.24 tons/ha. from the dense mulchings, about 1.33 tons/ha. from the moderate mulchings, and about 1.44 tons/ha. from the sparse mulchings respectively. The amounts of soil loss under these treatments are much lower than the standard of erosion in USDA (1939 Bennet). 3. Average numbers of germination by treatment are counted as 80 seedlings at the dense mulchings. 132 at the moderates and 121 at the sparse respectively. Large numbers of seedling are suppressed and died during the growing at the dense mulchings due to mainly mechanical obstruction. 4. Coarse straw-mat having about 70% of coverage density is the most suitable mulches in both soil erosion control and vegetation establishment. 5. The method of coarse straw-mat mulching is the most recommendable measure for establishing the vegetation cover with less soil erosion on the denuded gentle slopes in hillsides at present in Korea.