Land use and land cover (LULC) change is a major driver of environmental change in District Bahawalnagar, Punjab. LULC change can lead to changes in soil quality, water availability, and climate, all of which can affect crop yields. LULC change can also lead to the loss of agricultural land, forest land, water bodies, and an increment in Uban land that causes climate change and affects the agriculture sector. The study area showed that in the last thirty years, the population increased, built-up land increased, and agricultural land dropped by 30%. This study reviews the current state of knowledge on the impact of LULC on agriculture production in District Bahawalnagar. The conversion of agricultural land to urban development in the district of Bahawalnagar has led to a decline in crop yields of an average of 10%. The production of wheat and rice, the two major crops grown in District Bahawalnagar, is greatly influenced by LULC changes. The study also found that the loss of agricultural land has resulted in an increase in soil salinity, which has further reduced crop yields. The negative impacts of LULC change on agriculture production in the district of Bahawalnagar can be mitigated by adopting sustainable land management practices. These practices include reforestation, conservation agriculture, and water conservation. The government of Pakistan can also play a role in mitigating the negative impacts of LULC change on agriculture production by developing and implementing land use plans that protect agricultural land from conversion to other uses. More research is needed to better understand the impacts of LULC and develop effective management strategies. However, LULC is a major challenge that must be addressed if we are to ensure food security in the future.

Accurate crop yield estimation is paramount in agricultural monitoring and food security. In this study, we present a comprehensive investigation into estimating winter wheat yield in the Qazvin plane of Iran, leveraging the synergy between machine learning algorithms and the fusion of remote sensing data from radar and optical satellite sensors. The research is based on the availability of high-quality in situ yield data gathered by the Ministry of Agriculture in collaboration with the Food and Agriculture Organization (FAO), collected during the 2019-2020 crop year. The study area encompasses the Qazvin plane, an agriculturally significant region renowned for winter wheat production in Iran. In-situ data from various agricultural fields and seed types as reference measurements enabled us to conduct rigorous validation of the performance of machine learning algorithms and the effectiveness of the fused remote sensing data. The primary objective of this study is to assess and compare the performance of seven prominent machine learning algorithms for accurate estimation of the annual winter wheat yields. Additionally, we explored the potential of a proposed deep convolutional neural network (CNN) as a state-of-the-art approach for crop yield estimation, leveraging its ability to extract intricate spatial and spectral features from the remote sensing data. Through rigorous analysis of the pixel-level confusion matrices, we identify the most effective model for yield estimation, evaluating the complementarity and information redundancy between the two types of remote sensing data. In this study, we conducted an extensive comparison of various machine learning algorithms for winter wheat crop yield estimation. Among the four best-performing algorithms examined, namely polynomial regression (RMSE = 0.5657), random forest (RMSE = 0.1632), XGBoost (RMSE = 0.3153), and the proposed deep convolutional neural network (CNN) (RMSE = 0.1324), the CNN demonstrated superior performance. The CNN's yield estimation exceeded the total yearly agricultural statistics of Qazvin by 0.03 percent. However, this discrepancy can be attributed to various factors, including errors in wheat and barley fields mapping , mis-calculation in statistics, and the inherent limitations of yield estimation algorithms in capturing the dynamic nature of agricultural systems. The findings of this research provide valuable insights into the potential of machine learning algorithms and remote sensing data fusion for accurate crop yield estimation, paving the way for enhanced agricultural monitoring and decision-making processes in the region.

Urban Canopy Parameters (UCPs) are parameters, which are utilised to define thermal, radiative and roughness properties of urban areas, having significant impact on urban microclimate. The rapidly growing urbanization especially in developing region leads to modification in urban geometry, which calls for characterization of UCPs in the countries of such region to account for high population pressure, heterogeneous urban environment and subsequent impacts on global climate change. A research study conducted in Delhi, India found that Very High Resolution (VHR) optical satellite stereo datasets provide reasonable accuracy with respect to extraction of building height and footprints, which is further employed for computation of UCPs. However, the study evaluates only the key input parameters due to non- availability of 3D geodatabase. Hence, in this study an attempt has been made to evaluate all UCPs derived from VHR optical stereo along with key input parameters against reference data collected from field in the city of Bhubaneshwar, India. Performance evaluation with reference data derived UCPs shows that all the UCPs retrieved from VHR Optical Stereo data has high prediction accuracy. Overall bias, overall Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) from satellite derived UCPs was found to be better than 1m for most of the UCPs except for Building Surface Area to Plan Area Ratio, Height-to-width Ratio, and Complete Aspect Ratio which is found to be less than 2.7m. The correlation coefficient value were also observed to be more than 0.7 for most of the UCPs except Plan Area Density , Roughness Length and Frontal Area Density. The study concludes that UCPs derived from VHR Optical Stereo data has high accuracy even in the low -to-medium rise urban environment of study area. The study has high potential to be replicated in countries of developing region, which has similar development characteristics, and face resource and policy constraints with respect to availability of Airborne LiDAR and SAR data.

Hurricane Ian was a Category 5 system which developed in the Caribbean Sea in late September 2022. Ian achieved tropical storm strength on September 24, and reached hurricane strength on the next day. The storm moved north over western Cuba, and on September 27, at Category 5 strength, passed over the West Florida Shelf before making a September 28 landfall on the west coast of Florida near Sanibel Island. Ian subsequently crossed the Florida peninsula and into the Atlantic Ocean, gained strength, and made a second landfall on the South Carolina coast.

Following the passage of Hurricane Ian over the West Florida Shelf, true color images from the Moderate Resolution Imaging Spectroradiometers (MODIS) on the NASA Terra and Aqua satellites showed that nearly all of the southern West Florida Shelf was highly reflective, with peak backscatter at ~480 nm. This wavelength corresponds to the color "Maya Blue" (RGB - 115, 194, 251) and is indicative of surface suspension of fine carbonate (CaCO₃) sediments (mud) in tropical seas throughout the global ocean. Because of Ian's windspeed and strike properties it is likely that the water column was fully mixed to a depth of at least 60 m.

In the following days, a large plume of Maya Blue slurry was observed extending from west of the Dry Tortugas and curving to the east into the Straits of Florida. This discreet target offered a unique opportunity to quantify the slurry concentration.

Estimating the concentration of sediment in a plume of suspended carbonate by satellite sensor observations has been stymied up to now owing to a lack of in situ suspended sediment measurements during events such as Ian. “Sea truth” data for such events is difficult to acquire. However, the Particulate Inorganic Carbon (PIC) standard product provided by the Ocean Biology Distributed Active Archive Center (OBDAAC) is based on MODIS observations of a plume of coccolith chalk released from a ship in the “Chalk-Ex” experiment. Due to the similarities (particle size, mineralogy, and reflectance properties) of the suspended chalk features and the Ian-induced slurry, we utilized this data product to make initial estimates of the concentration of suspended sediment in the plume. Our results are in accord with historical measurements of storm-suspended sediment and show a range of 0.6-3.0 g/m3. These findings highlight a stark ignorance of process sedimentology as it unfolds during storms, and show the need for fast-response sampling of suspended sediment during events.

Most importantly, these estimates are an initial, unprecedented step for the broad application of satellite-derived suspension estimates during, and immediately subsequent to, sediment-mobilizing storms. As such, they are providing answers to basic questions in process sedimentology which have gone unanswered for over 80 years. With improved imagery and in-water sampling it will be possible to calculate total mass transport of carbonate from banks, platforms, and shelves worldwide.

In the study area, landslides represent the most frequent geological-geomorphological hazard in mountain environments, causing damage to infrastructure, local economies and loss of human lives. A landslide susceptibility map was developed, based on the sum of the weighted scores of the landslides conditioning factors. 21% of the study area is in high and very high susceptibility zones to be affected by landslides. These areas are concentrated in the headwaters of basins, valley bottoms, steep slopes and in the main riverbeds and streams.

Water clarity, measured by its transparency and turbidity, is a crucial characteristic for evaluating water quality. Water transparency could be defined as the extinction of light along the water column, conventionally estimated by Secchi disk depth. Remote sensing, particularly using Sentinel-2 imagery, has proven to be a valuable tool for monitoring water transparency in different bodies of water. In this study, a new algorithm was developed to estimate the Secchi disk depth in the Albufera de Valencia, a highly eutrophic coastal lagoon in Spain, using Sentinel-2 mission data. Three optical models (R490/R560, R490/R705, and R560/R705) were assessed for Secchi disk depth estimation. The R560/R705 model exhibited the best results and was selected for algorithm development and validation. The R560/R705 model achieved R² values of 0.6149 and 0.916 during calibration and validation, respectively, while the other models achieved an R² of 0.2805 (R490/R705) and 0.0043 (R490/R560). The new algorithm, obtained calibrating R560/R705 model, demonstrated an NRMSE of 17.8% in estimating Secchi disk depth in the Albufera of Valencia, compared to 20.7% for the previous one, indicating a significant improvement in algorithm performance and good accuracy in Secchi disk depth estimation in the Albufera of Valencia. Therefore, the new algorithm provides a more precise and reliable tool for estimating water clarity in the Albufera de Valencia using remote sensing data. This will contribute to better monitoring and management of water quality in this important aquatic ecosystem, valued for its natural and cultural heritage. Additionally, the results of this study highlight the importance of selecting appropriate optical models to estimate water clarity in highly turbid and eutrophic environments.

In recent decades, Chile's coastal areas have undergone significant transformations due to extreme events, intensification of tidal waves, and anthropogenic actions that have deepened coastal erosion. Currently, erosion rates in the Valparaíso region are irrefutable, with some beaches reaching -1.5 m/year and others, such as the Algarrobo Bay, up to -4.5 m/year. Given this scenario, beach monitoring poses excellent challenges for quantifying and projecting changes in sandy coastlines. Therefore, rigorous monitoring is required, based on low-cost, high-quality, and accurate data, involving the participation of coastal communities as fundamental axes in data capture. To achieve effective local monitoring, we have joined the Coastal Citizen Science (CoastSnap) program, developed by scientists at the Water Research Laboratory, University of New South Wales (UNSW) Sydney. This program has become a benchmark in coastal monitoring and a novel alternative for quantifying changes in marine-coastal environments. The implementation of the CoastSnap program in Chile has been carried out in the following phases: (i) Selection of the installation sites and taking of angles that will define the direction (yaw) and inclination (pitch) of the cell phone to achieve the expected visual; (ii) request for permits to install the platforms to the municipalities; (iii) design, signaling and, construction of the platforms; (iv) taking of control points (v) installation of the platforms; (vi) inauguration and start-up and (vii) extraction of the coastlines from the open repository GitHub, in the user profile Coastal Imaging Research Network (CIRN): https://github.com/Coastal-Imaging-Research-Network/CoastSnap-Toolbox. Eight CoastSnap platforms have been installed in the Valparaíso region on beaches (Papudo, Maitencillo, Reñaca, Viña del Mar, Caleta Portales, Algarrobo, Punta de Tralca and Santo Domingo). Since the installation of the first platform in August 2022, the community has shared approximately 350 photographs. The results show significant changes in the short term with beach widths averaging -20 m in San Alfonso del Mar beach.

Hyperspectral Imaging is getting popular in land use land classification because of its ability to capture detailed information through higher spatial resolution and contagious spectral bands. Using the hyperspectral image from G-LiHT (Goddard’s LiDAR, Hyperspectral, and Thermal) Airborne Imager covering a study area in Tennessee, Knoxville, we compared the performance of Spectral Angle Mappers (SAM), Spectral Information Divergence (SID), and Support Vector Machine (SVM) for land use land cover classification. We used a confusion matrix for the accuracy assessment of the classifiers. Among the three classifiers, SVM showed the highest accuracy with 92.03%. Our results also show that some classes, such as water and forests, are consistently distinguishable across all classification methods, while others, such as built-up areas vary depending on the technique used.

Deforestation is a global issue that affects forests worldwide, as they play a crucial role in mitigating climate change, conserving water resources, and generating rainfall. In Ecuador, extensive deforestation has been observed in various locations, such as Palmira in the province of Chimborazo, where constant afforestation and deforestation occur due to activities carried out by both public and private entities. Additionally, the area also exhibits desert areas due to erosion over the years.

This research focuses on the forest dynamics of four specific sites in Palmira: Jatun Loma, Galte Laime, Galte Cuatro Esquinas, and Palmira Dávalos. By utilizing the Google Earth Engine (GEE) platform and temporal trend analysis algorithms like LandTrendr and Continuous Change Detection and Classification (CCDC), satellite images were collected from 2000 to 2020. These images were processed to obtain time series based on the Normalized Difference Vegetation Index (NDVI).

The obtained results show trends that align with existing documentation regarding the constant afforestation and deforestation in the study area. Disturbance, recovery, and stability processes have been identified over the years. The research demonstrates the utility of LandTrendr and CCDC algorithms in analyzing forest dynamics and their relationship with human activities in Palmira.

In terms of results, an increase in forest area was observed in Galte Laime until approximately 2006, followed by significant deforestation. On the other hand, Palmira Dávalos, known as the Palmira Desert, exhibited a consistent lack of vegetation due to centuries of erosion. Galte Cuatro Esquinas showed a stable downward trend, followed by a regrowth starting in 2009. In Jatun Loma, stability was initially observed, followed by gradual deforestation and subsequent reforestation.

In conclusion, this research has provided a detailed description of the forest dynamics in the Palmira area using temporal trend analysis algorithms and satellite-based time series. The obtained results align with existing documentation on the constant afforestation and deforestation in the area. The importance of utilizing remote sensing tools and algorithms like LandTrendr to monitor and understand forest changes and their relationship with human activities is highlighted. These findings can contribute to decision-making in forest management and the conservation of natural resources in the study area.

Vegetation degradation is correlated with drought. The more drought intensifies, the more degraded vegetation increases.

Therefore, this study aimed to assess the correlation between rainfall and changes in the Normalized Difference Vegetation Index (NDVI) under arid and semi-arid conditions in Syria.

The study was carried out using annual rainfall data for (2012-2022 ) obtained from the Agricultural cloud seeding Project, to determine the average rainfall of the study area and to link it to the NDVI index of MODIS image data processed using the Google Earth Engine (GEE) for April of each year for the same time series. The results showed that the lowest NDVI value (0.098) was in (2016), representing the driest year during the studied series, while the highest NDVI value (2.4) was in 2019, which coincided with the highest rainfall rate of 206.67 mm, thus representing the less arid year during the same series.

It also found a strong correlation (R=0.7) between the overall average rainfall and the overall NDVI values of the studied time series.

The NDVI maps, which were classified as( -0.2 - 0.8), using ArcGIS 10.8.2, showed that arid land with a simple herbal coverage (0-0.1) occupied 90% of the total study area with the exception of 2019, where pastures and rain-fed crops (0.3-0.4) occupied 85.45% of the total study area. The study has shown that changes in the NDVI index are associated with changes in rainfall, indicating that they can be used to estimate and study drought as a simple method derived from satellite data in isolation from ground data.