• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.9-18
• /
• 2024

Small streams, despite their rich ecosystems, face challenges in vegetation assessment due to the limitations of traditional, time-consuming methods. This study presents a groundbreaking approach, combining unmanned aerial vehicles(UAVs), convolutional neural networks(CNNs), and the vegetation differential vegetation index (VDVI), to revolutionize both assessment and management of stream vegetation. Focusing on Idong Stream in South Korea (2.7 km long, 2.34 km² basin area)with eight diverse revetment methods, we leveraged high-resolution RGB images captured by UAVs across five dates (July-December). These images trained a ResNeXt101 CNN model, achieving an impressive 89% accuracy in classifying vegetation cover(soil,water, and vegetation). This enabled detailed spatial and temporal analysis of vegetation distribution. Further, VDVI calculations on classified vegetation areas allowed assessment of vegetation vitality. Our key findings showcase the power of this approach:(a) TheCNN model generated highly accurate cover maps, facilitating precise monitoring of vegetation changes overtime and space. (b) August displayed the highest average VDVI(0.24), indicating peak vegetation growth crucial for stabilizing streambanks and resisting flow. (c) Different revetment methods impacted vegetation vitality. Fieldstone sections exhibited initial high vitality followed by decline due to leaf browning. Block-type sections and the control group showed a gradual decline after peak growth. Interestingly, the "H environment block" exhibited minimal change, suggesting potential benefits for specific ecological functions.(d) Despite initial differences, all sections converged in vegetation distribution trends after 15 years due to the influence of surrounding vegetation. This study demonstrates the immense potential of UAV-based remote sensing and CNNs for revolutionizing small-stream vegetation assessment and management. By providing high-resolution, temporally detailed data, this approach offers distinct advantages over traditional methods, ultimately benefiting both the environment and surrounding communities through informed decision-making for improved stream health and ecological conservation.

• 한국수자원학회논문집
• /
• 제57권5호
• /
• pp.321-332
• /
• 2024

하천 공간의 지표 피복 현황 파악은 하천 관리 및 홍수 재해 예방에 필수적이다. 기존 조사 방법은 전문가에 의한 식생 판독을 통한 식생도 작도 방법이나 식생지수를 활용하는 방법이 활용되어 왔으나, 역동적으로 변화하는 하천 환경을 반영하기에 한계가 있다. 이러한 배경에서 본 연구는 내성천을 대상으로 위성영상 자료를 활용한 랜덤 포레스트 기법을 활용하여 다수 연도의 하천 내 식생 분포를 파악하고, 적용성을 검토하였다. 원격탐사 자료 Sentinel-2 위성 영상을 사용하였으며, 지상 참값(ground truth)은 2016년 내성천 지표 피복 자료를 활용하였다. 랜덤 포레스트 머신러닝 알고리듬을 활용하여 미리 선정된 10개 샘플링 영역으로부터 분류군 별로 1,000개의 표본을 추출하여 훈련 및 검증하였으며, 민감도 분석, 연도별 지표 피복 분석, 정확도 분석을 통하여 적용성을 평가하였다. 연구 결과, 검증 자료 기반의 정확도는 85.1%로 나타났다. 트리 수, 샘플 수, 하천 구역에 대한 민감도 분석 결과, 각각 30개, 800개, 하류에서 효율성이 높았다. 지표 분류 유형은 6개 항목에서 높은 정확도를 보여 지표 피복 분류 결과가 실제 하천 환경을 잘 반영하는 것으로 나타났다. 정확도 분석 결과, 전체 샘플 중 14.9%의 경계오류와 내부오류를 확인하였으며, 지표 피복 분류 중 산발 식생과 초본 식생을 제외한 항목들은 높은 정확도를 보였다. 본 연구에서는 단일 하천을 대상으로 적용하였지만, 보다 정확하고 많은 자료의 구축을 위해서는 다수의 하천에 대해 지표 피복 분류 기법의 적용이 요구된다.

• 한국농공학회지
• /
• 제38권2호
• /
• pp.123-132
• /
• 1996

The purpose of this study was to clarify the reflectance of soil and plant in order to extract the soil and vegetation informations using the satellite remote sensing data. The influence of soil moisture content and vegetation cover rate on the soil reflectance, and the relationship between vegetation reflectence and its vitality were discussed. The results obtained in this study were summarized as follows; I) The soil reflectance($R_{0.65}$) of wavelength ($0.65{\mu}m$) was closely related to the reflectance((($IR_{0.85}$) of wavelength $0.85{\mu}m$. This relationship could be expressed by soil line. 2) A point on the soil line was affected by the soil moisture ratio and the organic matter content. 3) The vegetation cover rate was formulated in terms of soil and vegetation reflectance at wavelengths pf $0.65{\mu}m$($R_{0.65}$) and ($0.85{\mu}m$) (($IR_{0.85}$). 4) The vegetation reflectence was strongly influenced by its vitality, which was related to the moisture content and the chlorophy [[-a concentration.

• 대한원격탐사학회지
• /
• 제29권4호
• /
• pp.351-360
• /
• 2013

MODIS NDVI 시계열 자료에 하모닉 분석을 적용하면 계절에 따른 식생의 연간 변화 패턴을 이해할 수 있다. 하모닉 분석은 시간에 따라 형성된 시계열 자료의 복잡한 파형의 형태를 일련의 정현파 파형(sinusoidal waves)의 합으로 분해하고 진폭과 위상으로 정의되는 각 파형의 특성을 통해 시계열 자료의 패턴을 분석하는 방법이다. 본 논문은 NDVI 시계열 자료에 하모닉 모형을 적용하여 각 구성 성분의 진폭과 위상을 측정하고 이러한 파라미터들의 변화를 분류하여 식생의 연간 변화를 탐지하는 방법론을 제안하고 있다. 이를 통해 장기간에 걸친 식생 변화 지역을 모니터링할 수 있고 또한, 이 과정에서 하모닉 모형을 통해 미관측 자료나 노이즈 자료를 복원하여 시계열자료를 재구축할 수 있는 장점도 있다. 본 연구에서는 시뮬레이션 자료를 통해 하모닉 분석의 유용성에 대해 테스트하였고, 2006년부터 2012년까지 총 7년간 북한 개마고원 부근의 MODIS NDVI 식생 자료에 하모닉 모형을 적용하여 연간 변화 지역을 탐지하고 연간 식생변화지역맵을 작성하였다. 이렇게 작성된 연간 식생변화지역맵은 장기적인 식생변화 모니터링을 위한 기초 맵으로 활용될 수 있을 것으로 기대된다.

• 대한공간정보학회지
• /
• 제19권4호
• /
• pp.153-159
• /
• 2011

식생의 토지피복은 지구시스템의 일반적인 순환이나 탄소 교환 모델을 설명하기 위한 중요한 변수이다. 본 연구의 동아시아지역의 식생의 상태를 모니터링하고 그에 따른 변화를 이해하는 것이 주목적이다. SPOT VGT센서로부터 취득된 1999년부터 2010년의 NDVI 10-day MVC자료를 이용하였으며 12년간의 토지피복 변화를 비교 분석하였다. 최종적으로 분류된 class를 토지피복에 따라 각각의 class에 해당하는 1999년과 2010년의 Dynamic zone과 Static zone을 나누어 Dynamic zone에 대한 positive change zone과 negative change zone에 대한 분석을 수행하였다. 따라서 각 class에 해당하는 피복들이 대다수 2010년으로 갈수록 변화가 나타나고 있으며 실제 사막지역이 동진하여 식생의 변화가 나타나고 있다는 것을 12년 동안의 자료를 분석하여 확인하였다.

• Journal of Ecology and Environment
• /
• 제43권2호
• /
• pp.202-211
• /
• 2019

Oceanic islands are biologically important for their unique assemblages of species and high levels of endemism and are sensitive to environmental change because of their isolation and small species source pools. Habitat destruction caused by human landscape development is generally accepted as the main cause of extinction on islands, with exotic species invasion a secondary cause of extinction, especially on tropical islands. However, secondary impacts of human development (e.g., general degradation through resource use and exotic species introduction) are understudied on temperate islands. To determine secondary impacts of human development on the understory vegetation community, 90 field sites on Ulleung Island, South Korea, were sampled during the summer of 2016. Understory vegetation was chosen as it is a proxy for ecosystem health. Diversity and percent cover of introduced, native, and endemic species were tested against proximity to developed areas and trail usage using a model selection approach. Diversity was also tested against percent cover of three naturalized species commonly found in survey plots. The main finding was that distance to development, distance to town, and trail usage have limited negative impacts on the understory vegetation community within best-supported models predicting native and introduced cover and diversity. However, endemic species cover was significantly lower on high usage trails. While there are no apparent locally invasive plant species on the island at the time of this study, percent cover of Robinia pseudoacacia, a naturalized tree species, negatively correlated with plot diversity. These findings indicate that forests on Ulleung Island are not experiencing a noticeable invasion of understory vegetation, and conservation efforts can be best spent preventing future invasions.

• 한국농공학회논문집
• /
• 제50권3호
• /
• pp.115-123
• /
• 2008

Evapotranspiration mapping using both meteorological ground-based measurements and satellite-derived information has been widely studied during the last few decades and various methods have been developed for this purpose. It is significant and necessary to estimate regional evapotranspiration (ET) distribution in the hydrology and water resource research. The study focused on analyzing the surface ET of Chungbuk region using Landsat 7 ETM imagery. For this process, we estimated the regional daily evapotranspiration on May 8, 2000. The estimation of surface evapotranspiration is based on the relationship between Temperature Vegetation Dryness Index (TVDI) and Morton's actual ET. TVDI is the relational expression between Normalized Difference of Vegetation Index (NDVI) and Land Surface Temperature (LST). The distribution of NDVI corresponds well with that of land-use/land cover in Chungbuk. The LST of several part of city in Chungbuk region is higher in comparison with the averaged LST. And TVDI corresponds too well with that of land cover/land use in Chungbuk region. The low evapotranspiration availability is distinguished over the large city like Cheongju-si, Chungju-si and the difference of evapotranspiration availability on forest and paddy is high.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.329-332
• /
• 2007

Annual vegetation growth patterns are determined by the intrinsic phenological characteristics of each land cover types. So, if typical growth patterns of each land cover types are well-estimated, and a NDVI time-series data of a certain area is compared to those estimated patterns, we can implement more advanced analyses such as a land surface-type classification or a land surface type change detection. In this study, we utilized Terra MODIS NDVI 250m data and compressed full annual NDVI time series data into several indices using the Harmonic Analysis of Time Series(HANTS) algorithm which extracts the most significant frequencies expected to be presented in the original NDVI time-series data. Then, we found these frequencies patterns, described by amplitude and phase data, were significantly different from each other according to vegetation types and these could be used for land cover classification. However, in spite of the capabilities of the HANTS algorithm for detecting and interpolating cloud-contaminated NDVI values, some distorted NDVI pixels of June, July and August, as well as the long rainy season in Korea, are not properly corrected. In particular, in the case of two or three successive NDVI time-series data, which are severely affected by clouds, the HANTS algorithm outputted wrong results.

• The Korean Journal of Ecology
• /
• 제25권1호
• /
• pp.9-17
• /
• 2002

Human activities greatly affect the environment causing its degradation. Urban development and road networks construction cause main impacts on ecosystems and particularly on vegetation cover: road constructions induce complete degradation of the vegetation cover and often leaves a hare land, sometimes without even a soil cover. Reconstitution of vegetation cover is necessary to limit superficial erosion and land slipping on the road, towards a reintegration of the site in the neighbouring landscape. Many approaches have been studied over the last 30 years aiming at this reconstitution of vegetation cover. At frost, the main purpose of land reclamation was to create a new ecosystem. At this time, the environment created was rather a "garden" with a new soil adapted to the plantation of "decorative" species. Then, in early 90′s many studies on the restoration ecology concept rather focused on adapting the vegetation to the existing conditions on the site, as in a side road embankment for example. Nowadays, we notice a large tendency towards the use of such adapted native species instead of industrially produced seeds. In southern France, our team have led research on the potentials of those local species for their use in revegetation processes with hydro-seeding. We therefore developed an approach combining the use of different types of species: Industrially produced, native and wild cultivated species. This method integrates the benefits of using available low costing seeds that are already used on large scale projects with better adapted species, issued form the cultivation of native species and seed production for their use on smaller scale and more costly but more effective results. The use of wild cultivated species seeds was developed in order to limit the cost and reduce harsh natural seed withdrawal in the natural environment In the case of the use of native species. Besides, the use of such seeds allowed a larger geographical scale of use than with local native seeds. In addition, our team began two years ago a research project in Lebanon aiming at the Introduction and development of the revegetation techniques in Lebanon. In fact, this country bared since 20 years the consequences of urban pressure on its environment especially by the development of quarries and road networks. Therefore, pioneer work is necessary to aim at the adaptation of these techniques to the local environment.

• 대한원격탐사학회지
• /
• 제20권3호
• /
• pp.197-205
• /
• 2004

Wetlands are lands with a mixture of water, herbaceous or woody vegetation and wet soil. And linear spectral mixture analysis (LSMA) is one of the most often used methods in handling the spectral mixture problem. This study aims to test LSMA is an enhanced routine for classification of wetland land-covers in Paldang reservoir and vicinity (paldang Reservoir) using Landsat TM and ETM+ imagery. In the LSMA process, reference endmembers were driven from scatter-plots of Landsat bands 3, 4 and 5, and a series of endmember models were developed based on green vegetation (GV), soil and water endmembers which are the main indicators of wetlands. To consider phenological characteristics of Paldang Reservoir, a soil endmember was subdivided into bright and dark soil endmembers in spring and a green vegetation (GV) endmember was subdivided into GV tree and GV herbaceous endmembers in fall. We found that LSMA fractions improved the classification accuracy of the wetland land-cover. Four endmember models provided better GV and soil discrimination and the root mean squared (RMS) errors were 0.011 and 0.0039, in spring and fall respectively. Phenologically, a fall image is more appropriate to classify wetland land-cover than spring's. The classification result using 4 endmember fractions of a fall image reached 85.2 and 74.2 percent of the producer's and user's accuracy respectively. This study shows that this routine will be an useful tool for identifying and monitoring the status of wetlands in Paldang Reservoir.