Automatic Mapping of Irrigated Areas in Mediteranean Context Using Landsat 8 Time Series Images and Random Forest Algorithm

Urban areas represent the primary source region of greenhouse gas emissions. Mapping urban areas is essential for understanding land cover change, carbon cycles, and climate change (urban areas also refer to impervious surfaces, i.e., artificial cover and structures). Remote sensing has greatly advanced urban areas mapping over the last several decades. At present, we have entered the era of big data. Long time series of satellite data such as Landsat and high-performance computing platforms such as Google Earth Engine (GEE) offer new opportunities to map urban areas. The objective of this research was to determine how annual time series images from Landsat 8 Operational Land Imager (OLI) can effectively be composed to map urban areas in three cities in China in support of GEE. Three reducer functions, ee.Reducer.min(), ee.Reducer.median(), and ee.Reducer.max() provided by GEE, were selected to construct four schemes to synthesize the annual intensive time series Landsat 8 OLI data for three cities in China. Then, urban areas were mapped based on the random forest algorithm and the accuracy was evaluated in detail. The results show that (1) the quality of annual composite images was improved significantly, particularly in reducing the impact of cloud and cloud shadows, and (2) the annual composite images obtained by the combination of multiple reducer functions had better performance than that obtained by a single reducer function. Further, the overall accuracy of urban areas mapping with the combination of multiple reducer functions exceeded 90% in all three cities in China. In summary, a suitable combination of reducer functions for synthesizing annual time series images can enhance data quality and ensure differences between characteristics and higher precision for urban areas mapping.

Download Full-text

Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition

Remote Sensing ◽

10.3390/rs12152411 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2411 ◽

Cited By ~ 2

Author(s):

Thanh Noi Phan ◽

Verena Kuch ◽

Lukas W. Lehnert

Keyword(s):

Time Series ◽

Random Forest ◽

Land Cover ◽

Land Cover Classification ◽

High Accuracy ◽

Google Earth ◽

Temporal Aggregation ◽

Google Earth Engine ◽

Time Series Images ◽

Land Cover Maps

Land cover information plays a vital role in many aspects of life, from scientific and economic to political. Accurate information about land cover affects the accuracy of all subsequent applications, therefore accurate and timely land cover information is in high demand. In land cover classification studies over the past decade, higher accuracies were produced when using time series satellite images than when using single date images. Recently, the availability of the Google Earth Engine (GEE), a cloud-based computing platform, has gained the attention of remote sensing based applications where temporal aggregation methods derived from time series images are widely applied (i.e., the use the metrics such as mean or median), instead of time series images. In GEE, many studies simply select as many images as possible to fill gaps without concerning how different year/season images might affect the classification accuracy. This study aims to analyze the effect of different composition methods, as well as different input images, on the classification results. We use Landsat 8 surface reflectance (L8sr) data with eight different combination strategies to produce and evaluate land cover maps for a study area in Mongolia. We implemented the experiment on the GEE platform with a widely applied algorithm, the Random Forest (RF) classifier. Our results show that all the eight datasets produced moderately to highly accurate land cover maps, with overall accuracy over 84.31%. Among the eight datasets, two time series datasets of summer scenes (images from 1 June to 30 September) produced the highest accuracy (89.80% and 89.70%), followed by the median composite of the same input images (88.74%). The difference between these three classifications was not significant based on the McNemar test (p > 0.05). However, significant difference (p < 0.05) was observed for all other pairs involving one of these three datasets. The results indicate that temporal aggregation (e.g., median) is a promising method, which not only significantly reduces data volume (resulting in an easier and faster analysis) but also produces an equally high accuracy as time series data. The spatial consistency among the classification results was relatively low compared to the general high accuracy, showing that the selection of the dataset used in any classification on GEE is an important and crucial step, because the input images for the composition play an essential role in land cover classification, particularly with snowy, cloudy and expansive areas like Mongolia.

Download Full-text

A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm

International Journal of Applied Earth Observation and Geoinformation ◽

10.1016/j.jag.2019.04.013 ◽

2019 ◽

Vol 80 ◽

pp. 127-136 ◽

Cited By ~ 4

Author(s):

Ana Cláudia dos Santos Luciano ◽

Michelle Cristina Araújo Picoli ◽

Jansle Vieira Rocha ◽

Daniel Garbellini Duft ◽

Rubens Augusto Camargo Lamparelli ◽

...

Keyword(s):

Time Series ◽

Random Forest ◽

Classification Scheme ◽

Regional Scale ◽

Space Time ◽

Random Forest Algorithm ◽

Landsat Images

Download Full-text

Estimation of rice phenology date using integrated HJ-1 CCD and Landsat-8 OLI vegetation indices time-series images

Journal of Zhejiang University SCIENCE B ◽

10.1631/jzus.b1500087 ◽

2015 ◽

Vol 16 (10) ◽

pp. 832-844 ◽

Cited By ~ 24

Author(s):

Jing Wang ◽

Jing-feng Huang ◽

Xiu-zhen Wang ◽

Meng-ting Jin ◽

Zhen Zhou ◽

...

Keyword(s):

Time Series ◽

Vegetation Indices ◽

Landsat 8 ◽

Landsat 8 Oli ◽

Time Series Images ◽

Rice Phenology

Download Full-text

Mapping Agricultural Landuse Patterns from Time Series of Landsat 8 Using Random Forest Based Hierarchial Approach

Remote Sensing ◽

10.3390/rs11050601 ◽

2019 ◽

Vol 11 (5) ◽

pp. 601 ◽

Cited By ~ 6

Author(s):

Sajid Pareeth ◽

Poolad Karimi ◽

Mojtaba Shafiei ◽

Charlotte De Fraiture

Keyword(s):

Land Use ◽

Time Series ◽

Random Forest ◽

Spatial Resolution ◽

Temporal Dynamics ◽

Learning Algorithm ◽

Open Data ◽

Landsat 8 ◽

Processing Scheme ◽

Irrigated Area

Increase in irrigated area, driven by demand for more food production, in the semi-arid regions of Asia and Africa is putting pressure on the already strained available water resources. To cope and manage this situation, monitoring spatial and temporal dynamics of the irrigated area land use at basin level is needed to ensure proper allocation of water. Publicly available satellite data at high spatial resolution and advances in remote sensing techniques offer a viable opportunity. In this study, we developed a new approach using time series of Landsat 8 (L8) data and Random Forest (RF) machine learning algorithm by introducing a hierarchical post-processing scheme to extract key Land Use Land Cover (LULC) types. We implemented this approach for Mashhad basin in Iran to develop a LULC map at 15 m spatial resolution with nine classes for the crop year 2015/2016. In addition, five irrigated land use types were extracted for three crop years—2013/2014, 2014/2015, and 2015/2016—using the RF models. The total irrigated area was estimated at 1796.16 km2, 1581.7 km2 and 1578.26 km2 for the cropping years 2013/2014, 2014/2015 and 2015/2016, respectively. The overall accuracy of the final LULC map was 87.2% with a kappa coefficient of 0.85. The methodology was implemented using open data and open source libraries. The ability of the RF models to extract key LULC types at basin level shows the usability of such approaches for operational near real time monitoring.

Download Full-text

Feature Comparison and Optimization for 30-M Winter Wheat Mapping Based on Landsat-8 and Sentinel-2 Data Using Random Forest Algorithm

Remote Sensing ◽

10.3390/rs11050535 ◽

2019 ◽

Vol 11 (5) ◽

pp. 535 ◽

Cited By ~ 4

Author(s):

Yuanhuizi He ◽

Changlin Wang ◽

Fang Chen ◽

Huicong Jia ◽

Dong Liang ◽

...

Keyword(s):

Random Forest ◽

Winter Wheat ◽

High Precision ◽

Agricultural Land ◽

Global Climate ◽

Machine Learning Algorithms ◽

Landsat 8 ◽

Spectral Indices ◽

Random Forest Algorithm ◽

Sentinel 2

Winter wheat cropland is one of the most important agricultural land-cover types affected by the global climate and human activity. Mapping 30-m winter wheat cropland can provide beneficial reference information that is necessary for understanding food security. To date, machine learning algorithms have become an effective tool for the rapid identification of winter wheat at regional scales. Algorithm implementation is based on constructing and selecting many features, which makes feature set optimization an important issue worthy of discussion. In this study, the accurate mapping of winter wheat at 30-m resolution was realized using Landsat-8 Operational Land Imager (OLI), Sentinel-2 Multispectral Imager (MSI) data, and a random forest algorithm. This paper also discusses the optimal combination of features suitable for cropland extraction. The results revealed that: (1) the random forest algorithm provided robust performance using multi-features (MFs), multi-feature subsets (MFSs), and multi-patterns (MPs) as input parameters. Moreover, the highest accuracy (94%) for winter wheat extraction occurred in three zones, including: pure farmland, urban mixed areas, and forest areas. (2) Spectral reflectance and the crop growth period were the most essential features for crop extraction. The MFSs combined with the three to four feature types enabled the high-precision extraction of 30-m winter wheat plots. (3) The extraction accuracy of winter wheat in three zones with multiple geographical environments was affected by certain dominant features, including spectral bands (B), spectral indices (S), and time-phase characteristics (D). Therefore, we can improve the winter wheat mapping accuracy of the three regional types by improving the spectral resolution, constructing effective spectral indices, and enriching vegetation information. The results of this paper can help effectively construct feature sets using the random forest algorithm, thus simplifying the feature construction workload and ensuring high-precision extraction results in future winter wheat mapping research.

Download Full-text

REMOTE SENSING IMAGE TIME SERIES METRICS FOR DISTINCTION BETWEEN PASTURE AND CROPLANDS USING THE RANDOM FOREST CLASSIFIER

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-3-w12-2020-557-2020 ◽

2020 ◽

Vol XLII-3/W12-2020 ◽

pp. 557-562

Author(s):

M. A. A. Rodrigues ◽

H. N. Bendini ◽

A. R. Soares ◽

T. S. Körting ◽

L. M. G. Fonseca

Keyword(s):

Remote Sensing ◽

Time Series ◽

Random Forest ◽

Landsat 8 ◽

Kappa Index ◽

Object Based ◽

One Year ◽

Global Accuracy ◽

Rural Production ◽

Potential Use

Abstract. Pasture and croplands play an important role in Brazil’s economic and political scenarios, once its PIB (Raw Internal Product) is mainly based on what is exported from the rural production, such as meat and soybean, and government, with its regulations, is part-responsible for the establishment and maintaining of the conditions so that the trades can go well. In addition, these two types of land use correspond together to aprox. one third of the country extension. Moreover, frequently lands occupation is subject of discussion concerning its potential use for the reason of conflicts including Brazilian traditional communities, landless people and big farmers. Considering it, mapping pasture and croplands accurately is crucial for the country administration, in both economic and political spheres. Certainly, remote sensing is the very manner to tackle this issue, although this may not be an easy task due to the spectral similarity between these patterns. This work, hence, aims to distinct pasture from croplands in an experimental subset area of Brazilian Cerrado biome, using remote sensing metric images derived from one-year time series of the Landsat 8 products. In order to achieve this goal, we utilized six bands of the OLI sensor and calculated seven metrics, attaining a compiled dataset with 42 layers. We performed an object-based supervised classification with the Random Forest algorithm, considering both spectral and geometrical attributes. Results showed global accuracy of 80%, with Kappa index of 0.6, and the potential time series have in separating targets spectrally similar.

Download Full-text

Pandemic velocity: Forecasting COVID-19 in the US with a machine learning & Bayesian time series compartmental model

PLoS Computational Biology ◽

10.1371/journal.pcbi.1008837 ◽

2021 ◽

Vol 17 (3) ◽

pp. e1008837

Author(s):

Gregory L. Watson ◽

Di Xiong ◽

Lu Zhang ◽

Joseph A. Zoller ◽

John Shamshoian ◽

...

Keyword(s):

New York ◽

Time Series ◽

Random Forest ◽

Compartmental Model ◽

Predictive Accuracy ◽

Population Level ◽

Random Forest Algorithm ◽

Case Count ◽

Uncertainty Estimates ◽

Bayesian Time Series

Predictions of COVID-19 case growth and mortality are critical to the decisions of political leaders, businesses, and individuals grappling with the pandemic. This predictive task is challenging due to the novelty of the virus, limited data, and dynamic political and societal responses. We embed a Bayesian time series model and a random forest algorithm within an epidemiological compartmental model for empirically grounded COVID-19 predictions. The Bayesian case model fits a location-specific curve to the velocity (first derivative) of the log transformed cumulative case count, borrowing strength across geographic locations and incorporating prior information to obtain a posterior distribution for case trajectories. The compartmental model uses this distribution and predicts deaths using a random forest algorithm trained on COVID-19 data and population-level characteristics, yielding daily projections and interval estimates for cases and deaths in U.S. states. We evaluated the model by training it on progressively longer periods of the pandemic and computing its predictive accuracy over 21-day forecasts. The substantial variation in predicted trajectories and associated uncertainty between states is illustrated by comparing three unique locations: New York, Colorado, and West Virginia. The sophistication and accuracy of this COVID-19 model offer reliable predictions and uncertainty estimates for the current trajectory of the pandemic in the U.S. and provide a platform for future predictions as shifting political and societal responses alter its course.

Download Full-text