A Study on Machine Learning-based Grass Demand Forecasting|RISS 상세보기

다국어 초록 (Multilingual Abstract)

The origin of the grass varies between regions and countries, but in the West, crops, which have been widely used for feed, have long been adapted to livestock grazing, and are derived from plants and perennials with good land cover capacity. In Korea, the origin of grass is different from that of the West. It has been used to decorate and cover the tomb's ground. Thus, Grass is one of the essential elements in our life. Grass is the major resource of various ecosystems and it also provides a space to relax. Nevertheless, Recently, Korea is recognized as a recession due to the reduction of new golf course construction and the slowdown of construction industry. However, since the 5-day system was implemented due to economic development and national income improvement after the Olympic and World Cup, the demand for grass as a green space for recreation and sports Is increasing. In particular, the use of new towns, the West Coast Saemangeum project, neighborhood parks, school grounds, and general residential gardens is increasing. Grass is expected to increase the value added of social indirect capital such as highways, the increase of golf population, the greening of urban and national lands using grass such as the increase of recreational activities and urban grass parks. In addition, the grass industry is a comprehensive field that includes the development, production, composition and management of garden, slope and sports. However, the grass industry is limited to production. This situation is lacking, and there is also a lack of basic data on the system or industry that can support the grass industry. Accordingly, we are necessary to have a research how we improve to use of grass and suggest newly methods with water demand.

번역하기

참고문헌 (Reference)

1 T. Ojha, "Wireless sensor networks for agriculture: The state-of-the-art in practice and future challenges" 118 : 66-84, 2015

2 Z. Mimi, "Statistical domestic water demand model for the west bank" 25 (25): 464-468, 2000

3 S. Kukal, "Soil matric potential-based irrigation scheduling to grass (oryza sativa)" 23 (23): 153-159, 2005

4 I. El-Magd, "Remote sensing and gis for estimation of irrigation crop water demand" 26 (26): 2359-2370, 2005

5 J. Timsina, "Productivity and management of grass–wheat cropping systems: issues and challenges" 69 (69): 93-132, 2001

6 S. K. Saleem, "Model predictive control for real-time irrigation scheduling" 46 (46): 299-304, 2013

7 I. Pulido-Calvo, "Improved irrigation water demand forecasting using a soft-computing hybrid model" 102 (102): 202-218, 2009

8 A. F. Torres, "Forecasting daily potential evapotranspiration using machine learning and limited climatic data" 98 (98): 553-562, 2011

9 K. Djaman, "Evapotranspiration, irrigation water requirement, and water productivity of grass (oryza sativa l.) in the sahelian environment" 15 (15): 469-482, 2017

10 P. Belder, "Effect of watersaving irrigation on grass yield and water use in typical lowland conditions in asia" 65 (65): 193-210, 2004