Analysis of Land Use and Land Cover Change Using Time-Series Data and Random Forest in North Korea

Abstract

North Korea being one of the most degraded forests globally has recently been emphasizing in forest restoration. Monitoring the trend of forest restoration in North Korea has important reference significance for regional environmental management and ecological security. Thus, this study constructed and analyzed a time-series land use land cover (LULC) map to identify the LULC changes (LULCCs) over extensive periods across North Korea and understand the forest change trends. The analysis of LULC used Landsat multi-temporal image and Random Forest algorithm on Google Earth Engine(GEE) from 2001 to 2018 in North Korea. Through the LULCC detection technique and consideration of the cropland change relation with elevation, the forest change in North Korea for 2001–2018 was evaluated. We extended the existing sampling methodology and obtained a higher overall accuracy (98.2% ± 1.6%), with corresponding kappa coefficients (0.959 ± 0.037), and improved the classification accuracy in cropland and forest cover. Through the change detection and spatial analysis, our research shows that the forests in the southern and central regions of North Korea are undergoing restoration. The sampling method we extended in this study can effectively and reliably monitoring the change trend of North Korea forests. It also provides an important reference for the regional environmental management and ecological security in North Korea.

Integrated Use of Optical and Radar Data for Cropland Mapping Over the Mountain Slope Area in Boyolali, Indonesia

“…Meanwhile, high producer's classification accuracies were identified for the class of water body (100%), forest (80%), and builtup area (70%). The result suggests that high accuracy is gained for the stable class such as water body (Piao et al, 2021).…”

“…Remote sensing technology plays a role in extracting and monitoring land cover which is known to have variations in spectral, temporal, and spatial resolution. Remote sensing with optical sensors has been widely used for land monitoring (Gumma et al, 2019;Piao et al, 2021;Sarono et al, 2015), but the image quality and accuracy of mapping using this sensor depends on atmospheric conditions. Primarily the use of optical data is a challenge due to high cloud interference in tropical countries.…”

“…These methods have advantages in terms of complex pattern retrieval capabilities and informative features of remote sensing satellite imagery. In this case, Random Forest (RF) was implemented for classification as it is known to improve the classification accuracy for time-series data without overfitting problem (Piao et al, 2021).…”

Pola Spasial Perubahan Tutupan Lahan/Penggunaan Lahan Menggunakan Google Earth Engine di Kabupaten Majalengka

“…Penelitian yang dilakukan oleh (Gandharum et al, 2022;Piao et al, 2021;Singha et al, 2019) menunjukan hasil penelitian bahwa penggunaan RF pada platform GEE dalam pemetaan penggunaan lahan dapat menghasilkan peta dengan akurasi tinggi dengan OA mencapai 92.6%. Hasil penelitian ini memiliki konsistensi dengan penelitian lain di mana gambar dan indeks gabungan dapat mencapai kurasi klasifikasi yang lebih tinggi daripada penggunaan hasil dari klasifikasi tunggal (Carrasco et al, 2019).…”

Land Cover and Land Use Mapping of the East Asian Summer Monsoon Region from 1982 to 2015

“…Sharma et al, (2016) utilized high-resolution imagery from the Landsat 8 Operational Land Imager to generate an LCLU map with a resolution of 30 m for Japan covering 2013-2015 [23]. Based on data from the same source, Piao et al (2021) reported changes in the forest cover of North Korea using 18 LCLU maps from 2001 to 2018 [24], and Hansen et al (2020) identified the tropical forest changes during same period [25]. In contrast, Seo et al (2014) mapped the landscape in the catchment of Haean in South Korea and documented the LCLU types for 2009-2011 via annual field campaigns [26].…”