Integration of Landsat and MODIS Imagery for Mapping 30-m Cotton Cultivation Areas in Xinjiang, China from 2000 to 2020

Cotton is a very important economic crop, which is not only an important strategic material related to the national livelihood, but also brings a lot of economic benefits and occupies an important position in the national economy. Cotton production in Xinjiang accounts for more than 80% of China’s cotton production, accounting for nearly one quarter of global cotton production. therefore, to do a good job in different growth cycles of cotton planting area, planting areas, cotton growth time changes and other basic information, for agricultural production departments and cotton farmers to make economic decisions and cotton planting structure adjustment is essential. At the same time, do a good job including cotton census and important crop growth monitoring, disaster warning, disaster assessment and post-disaster recovery work is also very important. And in recent years, with the continuous expansion of cotton cultivation area, scope and scale in Xinjiang, cotton is becoming increasingly important in the region’s economic and social development. Timely, accurate, and efficient acquisition of real-time cotton growth, monitoring of disaster conditions, acquisition and display of the extent and scope of damage, and post-disaster assessment in Xinjiang are of great importance for maintaining regional economic and provincial development and ensuring people’s well-being. Based on Google Earth Engine remote sensing big data cloud computing platform and high spatial and temporal resolution remote sensing image data Sentinel-2, this study takes Kuitun Reclamation Area of the Seventh Division of Xinjiang Production and Construction Corps, a typical cotton growing area in Xinjiang, as an example, and uses continuous time series image data combined with various indices (such as commonly used normalized vegetation index NDVI, normalized moisture index NDWI and cotton chlorophyll data SPAD), a time series analysis model was constructed to analyze the cotton growth conditions in different growing seasons in the study area. Based on the time series remote sensing data, the cotton change patterns and key temporal phase data of cotton in different months were extracted by the time series analysis method, and combined with the unique spectral information and texture features of cotton, the current mainstream high-precision threshold segmentation classification method was used to accurately and quickly extract the cotton planting area, planting range and cotton growth conditions in different growing stages, and the analysis of each feature information on the The contribution of each feature information to cotton extraction was analyzed. Combined with the ground real sampling data, the accuracy of cotton planting area and planting range extraction based on remote sensing images was verified, and the overall classification accuracy was above 90%, which is of great practical significance for the extraction and analysis of cotton information in this region. The online real-time big data processing engine, combined with a large number of remote sensing images with high spatial and temporal resolution, quickly and accurately identifies and extracts typical cotton planting areas in Xinjiang, which is of great significance and value to regional social development and crop extraction.

This article explores the efficacy of integrating Landsat and MODIS satellite imagery for comprehensive flood impact analysis. By employing advanced remote sensing technologies and sophisticated data processing techniques, this study offers a methodological framework that enhances the precision and depth of environmental analysis. The core methodology involves the systematic processing of satellite data, including radiometric and geometric corrections, combined with the use of analytical indices such as the Normalized Difference Water Index (NDWI) and the Enhanced Vegetation Index (EVI). These indices play a crucial role in accurately delineating water bodies and assessing the extent of flooding. The approach not only improves the reliability of flood mapping but also contributes to the broader understanding of environmental changes and aids in effective disaster management. Through this study, we demonstrate how strategic data integration can provide valuable insights for policymakers, enhancing responses to environmental crises.

Updated extent, area, and spatial distribution of tropical evergreen forests from inventory data provides valuable knowledge for research of the carbon cycle, biodiversity, and ecosystem services in tropical regions. However, acquiring these data in mountainous regions requires labor-intensive, often cost-prohibitive field protocols. Here, we report about validated methods to rapidly identify the spatial distribution of tropical forests, and obtain accurate extent estimates using phenology-based procedures that integrate the Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat imagery. Firstly, an analysis of temporal profiles of annual time-series MODIS Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Land Surface Water Index (LSWI) was developed to identify the key phenology phase for extraction of tropical evergreen forests in five typical lands cover types. Secondly, identification signatures of tropical evergreen forests were selected and their related thresholds were calculated based on Landsat NDVI, EVI, and LSWI extracted from ground true samples of different land cover types during the key phenology phase. Finally, a map of tropical evergreen forests was created by a pixel-based thresholding. The developed methods were tested in Xishuangbanna, China, and the results show: (1) Integration of Landsat and MODIS images performs well in extracting evergreen forests in tropical complex mountainous regions. The overall accuracy of the resulting map of the case study was 92%; (2) Annual time series of high-temporal-resolution remote sensing images (MODIS) can effectively be used for identification of the key phenology phase (between Julian Date 20 and 120) to extract tropical evergreen forested areas through analysis of NDVI, EVI, and LSWI of different land cover types; (3) NDVI and LSWI are two effective metrics (NDVI ≥ 0.670 and 0.447 ≥ LSWI ≥ 0.222) to depict evergreen forests from other land cover types during the key phenology phase in tropical complex mountainous regions. This method can make full use of the Landsat and MODIS archives as well as their advantages for tropical evergreen forests geospatial inventories, and is simple and easy to use. This method is suggested for use with other similar regions.

Mapping fractional woody cover in semi-arid savannahs using multi-seasonal composites from Landsat data

A primary activity required to support sustainable forest management is the detection and mitigation of forest disturbances. These disturbances can be planned, through urbanization and harvesting, or unplanned, through insect infestations or fire. Detection and characterization of disturbance types are important, as different disturbances have different ecological effects and may require unique managerial responses. As such, it is necessary for forest managers to have as complete and current information as possible to support decision making. In this study, we developed a framework to automatically detect and label disturbances derived from remotely sensed images. Disturbances were detected through traditional image differencing of medium-resolution imagery (Landsat-7 Enhanced Thematic Mapper Plus (ETM+), resampled to 30 m) but were refined and augmented through comparison with edge features extracted from high spatial resolution satellite imagery (Indian Remote Sensing (IRS) satellite 1C panchromatic imagery, resampled to 5 m). By incorporating spectral information, derived composite band values (tasselled cap transformations), spatial and contextual information, and secondary datasets, we were able to capture and label disturbance features with a high level of overall agreement (91%). Areal features, such as harvest areas, are captured and labelled more reliably than linear features such as roads, with 92% and 72% agreement when compared with control data, respectively. By incorporating rule-based disturbance attribution with remote sensing change detection, we envision the update of land cover databases with reduced human intervention, aiding more rapid data integration and opportunities for timely managerial responses.

Cultivating cotton and sustaining its productivity are challenging in temperate arid regions around the globe. Exploring suitable cotton cultivation areas to improve productivity in such climatic regions is essential. Thus, this study explores the ecologically suitable areas for cotton cultivation using the MaxEnt model, having 375 distribution points of long-staple cotton and various factors, including 19 climatic factors, 2 terrain factors, and 6 soil factors in Xinjiang. The area under the curve (AUC) of the predicted results was greater than 0.9, indicating that the model’s predictions had fairly high accuracy. However, the main environmental factors that affected the cotton’s growth were the lowest temperature in the coldest month, the hottest month, the precipitation in the driest season, and the monthly average temperature difference. Further, the temperature factors contributed 71%, while the contribution ratio of terrain and soil factors was only 22%. The research indicated that the current planting area was consistent with the predicted area in many areas of the study. Still, some areas, such as the Turpan region northwest of Bayingolin Mongol Autonomous Prefecture, are supposed to be suitable for planting cotton, but it is not planted. The current potential distribution area of long-staple cotton is mainly located in Aksu Prefecture and the northern part of the Kashgar Prefecture region. The climatic prediction shows that the growing area of long-staple cotton may expand to southern Altay, central Aksu, and Bortala Mongol Autonomous Prefecture. This study will be helpful for cotton cultivation suitability areas in Xinjiang and other regions with similar environments.

Recently land-use change has been the main concern for worldwide environment change and is being used by city and regional planners to design sustainable cities. Nakuru in the central Rift Valley of Kenya has undergone rapid urban growth in last decade. This paper focused on urban growth using multi-sensor satellite imageries and explored the potential benefits of combining data from optical sensors (Landsat, Worldview-2) with Radar sensor data from Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) data for urban land-use mapping. Landsat has sufficient spectral bands allowing for better delineation of urban green and impervious surface, Worldview-2 has a higher spatial resolution and facilitates urban growth mapping while PALSAR has higher temporal resolution compared to other operational sensors and has the capability of penetrating clouds irrespective of weather conditions and time of day, a condition prevalent in Nakuru, because it lies in a tropical area. Several classical and modern classifiers namely maximum likelihood (ML) and support vector machine (SVM) were applied for image classification and their performance assessed. The land-use data of the years 1986, 2000 and 2010 were compiled and analyzed using post classification comparison (PCC). The value of combining multi-temporal Landsat imagery and PALSAR was explored and achieved in this research. Our research illustrated that SVM algorithm yielded better results compared to ML. The integration of Landsat and ALOS PALSAR gave good results compared to when ALOS PAL- SAR was classified alone. 19.70 km2 of land changed to urban land-use from non-urban land-use between the years 2000 to 2010 indicating rapid urban growth has taken place. Land-use information is useful for the comprehensive land-use planning and an integrated management of resources to ensure sustainability of land and to achieve social Eq- uity, economic efficiency and environmental sustainability.

Historical and cultural area is an important part of urban settlement heritage space, and also an important carrier to inherit regional culture and rebrand the vitality of the old city. Based on the special regional tradition and religious culture of Xinjiang minority, and considering the problems such as the conflict between protection and renewal commonly encountered in the process of large-scale urbanization in recent years, this paper puts forward organic renewal approaches for historical and cultural areas, which is of great significance to the urban planning and development of western ethnic minority areas.

The cultivation area in Xinjiang, China has increased greatly in the recent 45 years, in some regions it has even increased 7 times since 1950 due to the oases development. We are trying to clarify the relationship between oases development and climate change in the oases during recent years. By analyzing the meteorological data obtained in some stations inside the oases in the recent 43 years, it was found that air temperature was increasing in winter, but decreasing in the suramer and precipitation was increasing in summer. In some places, precipitation has increased about 100 percent in the summer. By examining the effects of the oases on the climate improvement and detailing changes of the oases, the present study provides some detailed discussion on the oasis agricultural activities and environment changes and their effects on the climate change in Xinjiang, China.

Estimation of actual evapotranspiration (ET) for the Middle Rio Grande valley in central New Mexico via the METRIC surface energy balance model using MODIS and Landsat imagery is described. MODIS images are a useful resource for estimating ET at large scales when high spatial resolution is not required. One advantage of MODIS satellites is that images having a view angle < ~15° are potentially available about every four to five days. The main challenge of applying METRIC using MODIS is the selection of the two calibration conditions due to the low spatial resolution of MODIS. A calibration procedure specific to MODIS is described that utilizes the higher vegetation index areas of the image along with a consistently low ET location to develop the estimation function for sensible heat flux. This paper compares ET images for the Rio Grande region as produced by both MODIS and by Landsat. Application of METRIC energy balance processes along the Middle Rio Grande using MODIS imagery indicates that one can successfully produce monthly and annual ET estimates that are similar in value to those obtained using Landsat imagery if a cross-calibration scheme is considered. However, spatial fidelity is degraded.

Lakes are the most important water resource in arid and semi-arid regions and are good indicators of climate change. The study of lake expansion and contraction can reveal important information about climate change and regional responses. In this study, MOD09A1 global surface reflectance data of MODIS are used to extract the water areas of 12 main lakes in Xinjiang using a support vector machine method to investigate the temporal-spatial dynamics and driving factors of lake area variations between 2000 and 2017. The results indicate that (1) In general, the Xinjiang lakes exhibited large fluctuations between 2000 and 2017; the area of the lakes shrunk by 16.98 km2/year during 2007–2009 but expanded by 80.67 km2/year after 2010. (2) The changes in the Xinjiang lakes exhibited obvious spatial differences. There were strong fluctuations in the areas of the Tail-end lakes and the K value describing the degree of fluctuation in the lake area was 0.2%. The fluctuations in the areas of the Mountain lakes were more stable with a K value of 0.09% and the area of the Plateau lakes increased every year, with an annual increase of 19.90 km2. (3) The lakes with the larger fluctuations in the area were Ebinur Lake, Manasi Lake, and Barkol Lake, and the range of the areas was 370.85, 276.55, and 61.5 km2, respectively. Because of the regional diversity of Xinjiang, the driving forces that affect the area of the lakes differ in different areas. The main factors affecting the lake area change in the Tail-end lakes are the amount of inflowing water and the water use by agriculture and animal husbandry. The main reason for the stability of the Mountain lakes is the balance between water inflow and outflow. The main factor contributing to the expansion of the Plateau lakes area is the abundant supply of glacier/snow melt water. Overall, the main factor contributing to the expansion of Plateau lakes area is abundant glacier snow melt water supply. On the whole, the main factors affecting the temporal and spatial variation of the lake areas in Xinjiang are precipitation (r = .67, p = .003 < .01), temperature (r = .611, p = .007 < .01), and the increase in cultivated land area (r = −.021, p = .004 < .01).

This paper combines feature selection with machine learning algorithms to achieve object-oriented classification of crops in Gaofen-6 remote sensing images. The study provides technical support and methodological references for research on regional monitoring of food crops and precision agriculture management. “Staple-food-shifting” refers to the planting of other cash crops on cultivated land that should have been planted with staple crops such as wheat, rice, and maize, resulting in a change in the type of arable land cultivated. An accurate grasp of the spatial and temporal patterns of “staple-food-shifting” on arable land is an important basis for rationalizing land use and protecting food security. In this study, the Shihezi Reclamation Area in Xinjiang is selected as the study area, and Gaofen-6 satellite images are used to study the changes in the cultivated area of staple food crops and their regional distribution. Firstly, the images are segmented at multiple scales and four types of features are extracted, totaling sixty-five feature variables. Secondly, six feature selection algorithms are used to optimize the feature variables, and a total of nine feature combinations are designed. Finally, k-Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree (DT) are used as the basic models of image classification to explore the best combination of feature selection method and machine learning model suitable for wheat, maize, and cotton classification. The results show that our proposed optimal feature selection method (OFSM) can significantly improve the classification accuracy by up to 15.02% compared to the Random Forest Feature Importance Selection (RF-FI), Random Forest Recursive Feature Elimination (RF-RFE), and XGBoost Feature Importance Selection (XGBoost-FI) methods. Among them, the OF-RF-RFE model constructed based on KNN performs the best, with the overall accuracy, average user accuracy, average producer accuracy, and kappa coefficient reaching 90.68%, 87.86%, 86.68%, and 0.84, respectively.

Understanding land cover dynamics of protected areas is one area of active research and several studies have been done in this direction. However, such studies are limited with few parameters and lack a long-range spatial-temporal analysis to effectively understand land cover dynamics and thereby helping countries manage their protected areas sustainably. This research used Nyerere National Park (NNP) to explore its land cover dynamics from 1991 to 2021 and projected to 2050, vegetation health from 2000 to 2021 and surrounding human population from 1988 to 2021. The park’s land cover of 1991 and 2021 was explored using a smileCart classifier after training 897 samples of water, bareland, grassland, bushland and forest from the Landsat imagery. Its 2050 land cover was simulated using CA-Markov model. The park’s vegetation health was studied using NDVI and EVI from the Landsat and MODIS imagery. Land cover classes with significant changes are forest and grassland. The forest areas showed a decreasing trend from 62%-to-52%-to-41% from 1991-to-2021-to-2050, while the grassland areas showed an increasing trend from 9%-to-17%-to-24%. The maximum NDVI values from the Landsat imagery showed a minimal decrease from 0.76 in 1991 to 0.75 in 2021. Many park’s areas have weak vegetation based on the overall NDVI and EVI results. The study also identified rapid increase in human population around the park, and agricultural activities taking place in some of its areas. The results of this study provide a new reference to NNP and other studies in all other protected areas.

Cultivated land is an important prerequisite and guarantee for food production and security, and the change of cultivated land resources in China has always been concerned. National land survey is an effective way to accurately grasp the area and distribution of cultivated land resources. However, due to the differences in technical means and statistical standards at different stages, there are obvious breakpoints among the cultivated land area data of the three land surveys in China, which hinders the in-depth study of the spatio-temporal distribution of cultivated land resources in long-time series. The Autoregressive Integrated Moving Average model is used to reconstruct and mine the cultivated land area data from 1996 to 2019 based on the data of the third land survey in China. The spatio-temporal variation characteristics of cultivated land area are explored by using Geographic Information System spatial analysis, and the driving factors of cultivated land change are analyzed based on Geographical Detector (GeoDetector) from the perspective of social, economic, agricultural and natural. The results show that the area of cultivated land in China decreased continuously from 1996 to 2019, with a sharp decrease from 1996 to 2004 and a slow decrease from 2005 to 2019. From 1996 to 2019, there were obvious spatial differences in the change of cultivated land area in 31 provincial units. From 1996 to 2008, the cultivated land area in 29 provinces showed a downward trend, especially in the central and northern regions such as Shaanxi, Sichuan and Inner Mongolia. From 2008 to 2019, the cultivated land area in the underdeveloped areas of Heilongjiang, Jilin, Liaoning, Xinjiang, Gansu and Tibet increased significantly, while the rest showed a downward trend. Factor detection found that the q values of population, regional gross domestic product grain output, the proportion of the added value of the primary industry and average slope were all more than 0.5, which had an important impact on the change of cultivated land area. The explanatory power of the interaction between factors on the change of cultivated land area is enhanced in different degrees compared with the single factor effect, which is manifested in the enhancement of bilinear or nonlinear enhancement, and the interaction of different factors promotes the change of cultivated land area. The change of cultivated land area is the result of complex interaction between factors, and is closely related to the land policy in the same period.

Clarifying the dynamic changes in cultivated land and their driving factors is crucial for ensuring national food security and optimizing land use structure. This study focuses on the Alar Reclamation Area in southern Xinjiang, China, based on Landsat satellite images from seven key years (1990, 1994, 2000, 2006, 2010, 2015, and 2019) and corresponding socio-economic and meteorological data. Six machine learning algorithms—Spectral Angle Mapper (SAM), Artificial Neural Network (ANN), Minimum Distance Classification (MDC), Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Support Vector Machine–Conditional Random Field (SVM–CRF)—were compared to identify the optimal method for land use/cover classification. The results showed that the SVM–CRF algorithm achieved the highest accuracy (Overall Accuracy = 0.95; Kappa = 0.94). Cultivated land area increased by 729.97 km² from 1990 to 2019, showing an outward expansion trend. Path analysis, based on annual regional data, revealed that total population, GDP, total fixed asset investment, total agricultural output value, and cotton price were the major drivers. GDP had a negative direct effect on cultivated land area, reflecting industrialization and urban expansion. This study demonstrates that integrating machine learning classification with socio-economic and natural indicators provides a robust approach for understanding land use change mechanisms in arid oasis regions.