Cotton cultivated area detection and yield monitoring combining remote sensing with field data in lower Indus River basin, Pakistan.

As the Earth's population continuously increase with the passage of time, the demand for agricultural raw material for human need increases. It is critical to maintaining updated and accurate information about the dynamics and properties of the world agricultural systems. As cash crop, the updated information of the spatial distribution of cotton field is necessary to monitor the crop area and growth changes at regional level. We used 8-day enhanced vegetation index (EVI) time series to detect cotton crop area and binomial probabilistic approach to obtain the probability distribution of cotton crop occurrence. We used Gaussian kriging to derive cotton yield inside the detected cotton crop areas through crop reporting data. We also used field data from farmers to validate the cotton yield results. A strong correlation between the MODIS-derived cotton cultivated area and statistical data at the tehsil level were achieved (R2 = 0.84) for all study years (2004-2019). The total accuracy for the cotton crop area detection was 84.6% and yield prediction was 92.1%. Our study presents new approaches to map cotton area and yield, which are applicable to other regions through machine learning.

Effects of climate change on vegetation and snow cover area in Gilgit Baltistan using MODIS data.

The Hindukush-Karakoram-Himalaya (HKH) mountain ranges are the sources of Asia's most important river systems, which provide fresh water to 1.4 billion inhabitants in the region. Environmental and socioeconomic conditions are affected in many ways by climate change. Globally, climate change has received widespread attention, especially regarding seasonal and annual temperatures. Snow cover is vulnerable to climate warming, particularly temperature variations. By employing Moderate Resolution Imaging Spectroradiometer (MODIS) datasets and observed data, this study investigated the seasonal and interannual variability using snow cover, vegetation and land surface temperature (LST), and their spatial and temporal trend on different elevations from 2001 to 2020 in these variables in Gilgit Baltistan (GB), northern Pakistan. The study region was categorized into five elevation zones extending from < 2000 to > 7000 masl. Non-parametric Mann-Kendall trend tests and Sen's slope estimates indicate snow cover increases throughout the winter, but decreases significantly between June and July. In contrast, GB has an overall increasing annual LST trend. Pearson correlation coefficient (PCC) reveals a significant positive relationship between vegetation and LST (PCC = 0.73) and a significant negative relationship between LST and snow cover (PCC = - 0.74), and vegetation and snow cover (PCC = - 0.78). Observed temperature data and MODIS LST have a coefficient of determination greater than 0.59. Snow cover decreases at 3000-2000 masl elevations while increases at higher 5000 masl elevations.The vegetation in low and mid-elevation < 4000 masl zones decreases significantly annually. The temperature shows a sharply increasing trend at lower 2000-3000 masl elevations in the autumn, indicating the shifting of the winter seasons at this elevation zone. These findings better explain the spatiotemporal variations in snow cover, vegetation, and LST at various elevation zones and the interactions between these parameters at various elevations across the HKH region.