• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.2
• /
• pp.80-98
• /
• 2023

This study explores the effectiveness of various data preprocessing algorithms for improving subseasonal to seasonal (S2S) climate predictions from six climate forecast models and their Multi-Model Ensemble (MME) using a deep learning-based postprocessing model. A pipeline of data transformation algorithms was constructed to convert raw S2S prediction data into the training data processed with several statistical distribution. A dimensionality reduction algorithm for selecting features through rankings of correlation coefficients between the observed and the input data. The training model in the study was designed with TimeDistributed wrapper applied to all convolutional layers of U-Net: The TimeDistributed wrapper allows a U-Net convolutional layer to be directly applied to 5-dimensional time series data while maintaining the time axis of data, but every input should be at least 3D in U-Net. We found that Robust and Standard transformation algorithms are most suitable for improving S2S predictions. The dimensionality reduction based on feature selections did not significantly improve predictions of daily precipitation for six climate models and even worsened predictions of daily maximum and minimum temperatures. While deep learning-based postprocessing was also improved MME S2S precipitation predictions, it did not have a significant effect on temperature predictions, particularly for the lead time of weeks 1 and 2. Further research is needed to develop an optimal deep learning model for improving S2S temperature predictions by testing various models and parameters.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.303-303
• /
• 2017

Japanese agriculture has faced to several threats: aging and decrease of farmer population, global competition, and the risk of climate change as well as harsh and variable weather. On the other hands, the number of large scale farms is increasing, because farm lands have been being aggregated to fewer numbers of farms. Cost cutting, development of efficient ways to manage complicatedly scattered farm lands, maintaining yield and quality under variable weather conditions, are required to adapt to changing environments. Information and communications technology (ICT) would contribute to solve such problems and to create innovative technologies. Thus we have been developing an early warning and decision support system to reduce weather and climate risks for rice, wheat and soybean production in Japan. The concept and prototype of the system will be shown. The system consists of a weather data system (Agro-Meteorological Grid Square Data System, AMGSDS), decision support contents where information is automatically created by crop models and delivers information to users via internet. AMGSDS combines JMA's Automated Meteorological Data Acquisition System (AMeDAS) data, numerical weather forecast data and normal values, for all of Japan with about 1km Grid Square throughout years. Our climate-smart system provides information on the prediction of crop phenology, created with weather forecast data and crop phenology models, as an important function. The system also makes recommendations for crop management, such as nitrogen-topdressing, suitable harvest time, water control, pesticide spray. We are also developing methods to perform risk analysis on weather-related damage to crop production. For example, we have developed an algorism to determine the best transplanting date in rice under a given environment, using the results of multi-year simulation, in order to answer the question "when is the best transplanting date to minimize yield loss, to avoid low temperature damage and to avoid high temperature damage?".

• Atmosphere
• /
• v.30 no.4
• /
• pp.361-376
• /
• 2020

This study evaluates multiple Regional Climate Models (RCMs) in simulating temperature and precipitation over the Far East Asia (FEA) and estimates the portions of the total uncertainty originating in the RCMs and the driving Global Climate Models (GCMs) using nine present-day (1981~2000) climate data obtained from combinations of three GCMs and three RCMs in the CORDEX-EA phase2. Downscaling using the RCMs generally improves the present temperature and precipitation simulated in the GCMs. The mean temperature climate in the RCM simulations is similar to that in the GCMs; however, RCMs yield notably better spatial variability than the GCMs. In particular, the RCMs generally yield positive added values to the variability of the summer temperature and the winter precipitation. Evaluating the uncertainties by the GCMs (VARGCM) and the RCMs (VARRCM) on the basis of two-way ANOVA shows that VARRCM is greater than VARGCM in contrast to previous studies which showed VARGCM is larger. In particular, in the winter temperature, the ocean has a very large VARRCM of up to 30%. Precipitation shows that VARRCM is greater than VARGCM in all seasons, but the difference is insignificant. In the following study, we will analyze how the uncertainty of the climate model in the present-day period affects future climate change prospects.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.53-62
• /
• 2024

In this study, we built a model to estimate frost occurrence in South Korea using single-input deep learning and multi-input deep learning. Meteorological factors used as learning data included minimum temperature, wind speed, relative humidity, cloud cover, and precipitation. As a result of statistical analysis for each factor on days when frost occurred and days when frost did not occur, significant differences were found. When evaluating the frost occurrence models based on single-input deep learning and multi-input deep learning model, the model using both GRU and MLP was highest accuracy at 0.8774 on average. As a result, it was found that frost occurrence model adopting multi-input deep learning improved performance more than using MLP, LSTM, GRU respectively.

• Journal of Environmental Impact Assessment
• /
• v.27 no.5
• /
• pp.489-508
• /
• 2018

As climate changes, it is necessary to predict changes in the habitat environment in order to establish more aggressive adaptation strategies. The bioclimatic classification which clusters of areas with similar habitats can provide a useful ecosystem management framework. Therefore, in this study, biological habitat environment of Northeast Asia was identified through the establishment of the bioclimatic zones, and the impac of climate change on the biological habitat was analyzed. An ISODATA clustering was used to classify Northeast Asia (NEA)into 15 bioclimatic zones, and climate change impacts were predicted by projecting the future spatial distribution of bioclimatic zones based upon an ensemble of 17 GCMs across RCP4.5 and 8.5 scenarios for 2050s, and 2070s. Results demonstrated that significant changes in bioclimatic conditions can be expected throughout the NEA by 2050s and 2070s. The overall zones moved upward, and some zones were predicted to be greatly expanded or shrunk where we suggested as regions requiring intensive management. This analysis provides the basis for understanding potential impacts of climate change on biodiversity and ecosystem. Also, this could be used more effectively to support decision making on climate change adaptation.

• Atmosphere
• /
• v.20 no.2
• /
• pp.111-130
• /
• 2010

An uncertainty assessment for precipitation datasets simulated by Atmosphere-Ocean Coupled General Circulation Model (AOGCM) is conducted to provide reliable climate scenario over East Asia. Most of results overestimate precipitation compared to the observational data (wet bias) in spring-fall-winter, while they underestimate precipitation (dry bias) in summer in East Asia. Higher spatial resolution model shows better performances in simulation of precipitation. To assess the uncertainty of spatiotemporal precipitation in East Asia, the cyclostationary empirical orthogonal function (CSEOF) analysis is applied. An annual cycle of precipitation obtained from the CSEOF analysis accounts for the biggest variability in its total variability. A comparison between annual cycles of observed and modeled precipitation anomalies shows distinct differences: 1) positive precipitation anomalies of the multi-model ensemble (MME) for 20 models (thereafter MME20) in summer locate toward the north compared to the observational data so that it cannot explain summer monsoon rainfalls across Korea and Japan. 2) The onset of summer monsoon in MME20 in Korean peninsula starts earlier than observed one. These differences show the uncertainty of modeled precipitation. Also the comparison provides the criteria of annual cycle and correlation between modeled and observational data which helps to select best models and generate a new MME, which is better than the MME20. The spatiotemporal deviation of precipitation is significantly associated with lower-level circulations. In particular, lower-level moisture transports from the warm pool of the western Pacific and corresponding moisture convergence significantly are strongly associated with summer rainfalls. These lower-level circulations physically consistent with precipitation give insight into description of the reason in the monsoon of East Asia why behaviors of individually modeled precipitation differ from that of observation.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.4
• /
• pp.306-317
• /
• 2017

Unmanned aerial vehicles (UAVs) became popular platforms for the collection of remotely sensed data in the last years. This study deals with the monitoring of multi-temporal onion growth with very high resolution by means of low-cost equipment. The concept of the monitoring was estimation of multi-temporal onion growth using normalized difference vegetation index (NDVI) and meteorological factors. For this study, UAV imagery was taken on the Changnyeong, Hapcheon and Muan regions eight times from early February to late June during the onion growing season. In precision agriculture frequent remote sensing on such scales during the vegetation period provided important spatial information on the crop status. Meanwhile, four plant growth parameters, plant height (P.H.), leaf number (L.N.), plant diameter (P.D.) and fresh weight (F.W.) were measured for about three hundred plants (twenty plants per plot) for each field campaign. Three meteorological factors included average temperature, rainfall and irradiation over an entire onion growth period. The multiple linear regression models were suggested by using stepwise regression in the extraction of independent variables. As a result, $NDVI_{UAV}$ and rainfall in the model explain 88% and 68% of the P.H. and F.W. with a root mean square error (RMSE) of 7.29 cm and 59.47 g, respectively. And $NDVI_{UAV}$ in the model explain 43% of the L.N. with a RMSE of 0.96. These lead to the result that the characteristics of variations in onion growth according to $NDVI_{UAV}$ and other meteorological factors were well reflected in the model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.1
• /
• pp.144-158
• /
• 2012

A higher spatial resolution is preferable to support the accuracy of detailed climate analysis in urban areas. Airborne LiDAR (Light Detection And Ranging) and satellite (KOMPSAT-2, Korea Multi-Purpose Satellite-2) images at 1 to 4 m resolution were utilized to produce digital elevation and building surface models as well as land cover maps at very high(5m) resolution. The Climate Analysis Seoul(CAS) was used to calculate the fractional coverage of land cover classes in built-up areas and thermal capacity of the buildings from their areal volumes. It then produced analyzed maps of local-scale temperature based on the old and new input data. For the verification of the accuracy improvement by the precise input data, the analyzed maps were compared to the surface temperature derived from the ASTER satellite image and to the ground observation at our detailed study region. After the enhancement, the ASTER temperature was highly correlated with the analyzed temperature at building (BS) areas (R=0.76) whereas there observed no correlation with the old input data. The difference of the air temperature deviation was reduced from 1.27 to 0.70K by the enhancement. The enhanced precision of the input data yielded reasonable and more accurate local-scale temperature analysis based on realistic surface models in built-up areas. The improved analysis tools can help urban planners evaluating their design scenarios to be prepared for the urban climate.

• Journal of Climate Change Research
• /
• v.9 no.2
• /
• pp.143-156
• /
• 2018

Evapotranspiration is a key element in designing and operating agricultural hydraulic structures. The profound effect of climate change to local agro-hydrological systems makes it inevitable to study the potential variability in evapotranspiration rate in order to develop policies on future agricultural water management as well as to evaluate changes in agricultural environment. The APEX-Paddy model was used to simulate local evapotranspiration responses to climate change scenarios. Nine Global Climate Models(GCMs) downscaled using a non-parametric quantile mapping method and a Multi?Model Ensemble method(MME) were used for an uncertainty analysis in the climate scenarios. Results indicate that APEX-Paddy and the downscaled 9 GCMs reproduce evapotranspiration accurately for historical period(1976~2005). For future periods, simulated evapotranspiration rate under the RCP 4.5 scenario showed increasing trends by -1.31%, 2.21% and 4.32% for 2025s(2011~2040), 2055s(2041~2070) and 2085s(2071~2100), respectively, compared with historical(441.6 mm). Similar trends were found under the RCP 8.5 scenario with the rates of increase by 0.00%, 4.67%, and 7.41% for the near?term, mid?term, and long?term periods. Monthly evapotranspiration was predicted to be the highest in August, July was the month having a strong upward trend while. September and October were the months showing downward trends in evapotranspiration are mainly resulted from the shortening of the growth period of paddy rice due to temperature increase and stomatal closer as ambient $CO_2$ concentration increases in the future.

• Atmosphere
• /
• v.24 no.3
• /
• pp.403-417
• /
• 2014

Future changes in seasonal mean temperature and precipitation over East Asia under anthropogenic global warming are investigated by comparing the historical run for 1979~2005 and the Representative Concentration Pathway (RCP) 4.5 run for 2006~2100 with 20 coupled models which participated in the phase five of Coupled Model Inter-comparison Project (CMIP5). Although an increase in future temperature over the East Asian monsoon region has been commonly accepted, the prediction of future precipitation under global warming still has considerable uncertainties with a large inter-model spread. Thus, we select best five models, based on the evaluation of models' performance in present climate for boreal summer and winter seasons, to reduce uncertainties in future projection. Overall, the CMIP5 models better simulate climatological temperature and precipitation over East Asia than the phase 3 of CMIP and the five best models' multi-model ensemble (B5MME) has better performance than all 20 models' multi-model ensemble (MME). Under anthropogenic global warming, significant increases are expected in both temperature and land-ocean thermal contrast over the entire East Asia region during both seasons for near and long term future. The contrast of future precipitation in winter between land and ocean will decrease over East Asia whereas that in summer particularly over the Korean Peninsula, associated with the Changma, will increase. Taking into account model validation and uncertainty estimation, this study has made an effort on providing a more reliable range of future change for temperature and precipitation particularly over the Korean Peninsula than previous studies.