Assessing spatio-temporal mapping and monitoring of climatic variability using SPEI and RF machine learning models

Wahla, Saadia Sultan; Kazmi, Jamil Hasan; Sharifi, Alireza; Shirazi, Safdar Ali; Tariq, Aqil; Smith, Hayley Joyell

doi:10.1080/10106049.2022.2093411

Cited by 51 publications

(19 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the application of the Bayes rule conditionally, NBT allows datasets to be trained in less time. This is because it treats all vectors as though they are independent [ 63 ]. equation (5) of the Bayes can be explained as follows:

Where

represent the conditional probability of

given

;

showed the conditional probability of

given

.…”

Section: Methodsmentioning

confidence: 99%

Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data

Tariq¹,

Jiango²,

Li³

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

Where

represent the conditional probability of

given

;

showed the conditional probability of

given

.…”

Section: Methodsmentioning

confidence: 99%

Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data

Tariq¹,

Jiango²,

Li³

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

“…Moreover, an Object-Based Image Analysis (OBIA) approach [10] was proposed using Sentinel-1 SAR and Sentinel-2 data. Three machine-learning algorithms, including classification and regression tree (CART) [12], Random Forest (RF) [13,14], and Support Vector Machines (SVM) [15], were carried out. The results showed that the SVM and RF classifiers performed better than the CART classifier in the Overall Accuracy (OA) and kappa accuracy in most cases.…”

Section: Introductionmentioning

confidence: 99%

Timely Plastic-Mulched Cropland Extraction Method from Complex Mixed Surfaces in Arid Regions

Cheng

Qin

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Plastic mulch is extensively applied in agricultural production in arid regions. It significantly influences the interactions between land and atmosphere by altering underlying surface characteristics. An accurate and timely extraction method for Plastic-Mulched Cropland (PMC) is required to understand land surface energy transfer processes, eco-hydrological cycle, the climate effect of PMC, and in the management of water resources. In this study, we proposed a Timely Plastic-mulched cropland Extraction Method (TPEM) from complex mixed surfaces with multi-source remote sensing data in the Shiyanghe River Basin (SRB), a typical representation of a complex and inhomogeneous arid region in the northwest of China. We defined TPEM in three phases; in the first phase, the spectral characteristic curves were drawn from ground object points labeled by visual interpretation with multi-source remote sensing data. In the second phase, a spectral characteristic analysis of the modified index was proposed to amplify the difference between PMC and non-PMC ground objects. Finally, the Classification and Regression Tree (CART) classifier was used to generate thresholds of indices as PMC extraction rules. The results showed that it can extract the boundary of PMC in large-scale farmland, distinguish PMC from ground objects in complex mixed surfaces, and separate the PMC from desert land that shares same spectral characteristics with PMC. The TPEM is verified to be efficient and robust, with an overall accuracy of 0.9234, quantity disagreement of 0.0541, and allocation disagreement of 0.0224, and outperformed two extensively used PMC extraction methods, especially for timely PMC extraction when satellite data only during the period that ground surface incomplete covered by plastic mulch is available. This study will provide us with an accurate and timely method to extract PMC, especially in the widely distributed complex mixed surfaces.

show abstract

“…T HE major concerns of the modern society include crop and food security, and crop production and management are facing challenges due to population growth and environmental changes [1], [2], [3]. Crop-type classification provides essential information for various decision-making processes required to manage agricultural resources [4].…”

Section: Introductionmentioning

confidence: 99%

Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning Algorithms

Farmonov

Amankulova

Szatmári

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Developments in space-based hyperspectral sensors, advanced remote sensing, and machine learning can help crop yield measurement, modelling, prediction, and crop monitoring for loss prevention and global food security. However, precise and continuous spectral signatures, important for large-area crop growth monitoring and early prediction of yield production with cutting-edge algorithms, can be only provided via hyperspectral imaging. Therefore, this article used new-generation Deutsches Zentrum für Luft-und Raumfahrt Earth Sensing Imaging Spectrometer (DESIS) images to classify the main crop types (hybrid corn, soybean, sunflower, and winter wheat) in Mezőhegyes (southeastern Hungary). A Wavelet-attention convolutional neural network (WA-CNN), random forest and support vector machine (SVM) algorithms were utilized to automatically map the crops over the agricultural lands. The best accuracy was achieved with the WA-CNN, a feature-based deep learning algorithm and a combination of two images with overall accuracy (OA) value of 97.89%and the user's accuracy producer's accuracy was from 97% to 99%. To obtain this, first, factor analysis was introduced to decrease the size of the hyperspectral image data cube. A wavelet transform was applied to extract important features and combined with the spectral attention mechanism CNN to gain higher accuracy in mapping crop types. Followed by SVM algorithm reported OA of 87.79%, with the producer's and user's accuracies of its classes ranging from 79.62% to 96.48% and from 79.63% to 95.73%, respectively. These results demonstrate the potentiality of DESIS data to observe the growth of different crop types and predict the harvest volume, which is crucial for farmers, smallholders, and decision-makers.

show abstract

Assessing spatio-temporal mapping and monitoring of climatic variability using SPEI and RF machine learning models

Cited by 51 publications

References 63 publications

Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data

Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data

Timely Plastic-Mulched Cropland Extraction Method from Complex Mixed Surfaces in Arid Regions

Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning Algorithms

Contact Info

Product

Resources

About