Deep-learning based down-scaling of summer monsoon rainfall data over Indian region
Indian Institute of Tropical Meteorology, Ministry of Earth Sciences（印度热带气象研究所，地球科学部）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Ramrao Adik Institute of Technology（拉姆劳·阿迪克技术学院）；Defence Institute of Advanced Technology（国防高级技术研究所）
Bipin Kumar, Rajib Chattopadhyay, Manmeet Singh, Niraj Chaudhari, Karthik Kodari, Amit Barve
Downscaling is necessary to generate high-resolution observation data to validate the climate model forecast or monitor rainfall at the micro-regional level operationally. Dynamical and statistical downscaling models are often used to get information at high-resolution gridded data over larger domains. As rainfall variability is dependent on the complex Spatio-temporal process leading to non-linear or chaotic Spatio-temporal variations, no single downscaling method can be considered efficient enough. In data with complex topographies, quasi-periodicities, and non-linearities, deep Learning (DL) based methods provide an efficient solution in downscaling rainfall data for regional climate forecasting and real-time rainfall observation data at high spatial resolutions. In this work, we employed three deep learning-based algorithms derived from the super-resolution convolutional neural network (SRCNN) methods, to precipitation data, in particular, IMD and TRMM data to produce 4x-times high-resolution downscaled rainfall data during the summer monsoon season. Among the three algorithms, namely SRCNN, stacked SRCNN, and DeepSD, employed here, the best spatial distribution of rainfall amplitude and minimum root-mean-square error is produced by DeepSD based downscaling. Hence, the use of the DeepSD algorithm is advocated for future use. We found that spatial discontinuity in amplitude and intensity rainfall patterns is the main obstacle in the downscaling of precipitation. Furthermore, we applied these methods for model data postprocessing, in particular, ERA5 data. Downscaled ERA5 rainfall data show a much better distribution of spatial covariance and temporal variance when compared with observation.
Rainfall in Kerala State, the southern part of Indian Peninsula in particular is caused by the two monsoons and the two cyclones every year. In general, climate and rainfall are highly nonlinear phenomena in nature giving rise to what is known as the `butterfly effect'. We however attempt to train an ABF neural network on the time series rainfall data and show for the first time that in spite of the fluctuations resulting from the nonlinearity in the system, the trends in the rainfall pattern in this corner of the globe have remained unaffected over the past 87 years from 1893 to 1980. We also…
Summer monsoon rainfall over India depends on synoptic-scale phenomena like lows and depressions. India's summer monsoon season 2020 saw above-average rainfall. North Indian Ocean had 12 LPAs in summer 2020 in JJAS season. This monsoon season has the highest all-India rainfall since 1976 in August 2020. 50% of seasonal LPAs emerged in August 2020, but none intensified into a monsoon depression (MDs). This study explores the potential factors behind LPAs not intensifying/concentrating as MDs. Warming over the Northern Parts of the Arabian Sea (NPAS) boosted convection in August 2020, resulting …
The LNM Institute of Information Technology（LNM信息技术研究所）
Importance of monsoon rainfall cannot be ignored as it affects round the year activities ranging from agriculture to industrial. Accurate rainfall estimation and prediction is very helpful in decision making in the sectors of water resource management and agriculture. Due to dynamic nature of monsoon rainfall, it's accurate prediction becomes very challenging task. In this paper, we analyze and evaluate various deep learning approaches such as one dimensional Convolutional Neutral Network, Multi-layer Perceptron and Wide Deep Neural Networks for the prediction of summer monsoon rainfall in Ind…
The East Asian summer monsoon (EASM) is important for bringing rainfall to large areas of China. Historically, variations in the EASM have had major impacts including flooding and drought. We present an analysis of the impact of anthropogenic climate change on EASM rainfall in Eastern China using a newly updated attribution system. Our results suggest that anthropogenic climate change has led to an overall decrease in total monsoon rainfall over the past 65 years, and an increased number of dry days. However the model also predicts that anthropogenic forcings have caused the most extreme heavy…
Four case studies of cyclonic vortices over the Indian peninsular region during northeast monsoon season are presented. It was observed that the propagation of vortices over the peninsular orography was controlled by the vortex Froude number, Frv = Vmax/(NH), where, Vmax is the maximum tangential velocity of winds in the vortex, H is the height of the orography, and N is the Brunt-Vaisala frequency of atmosphere along the orography. Strong vortices with Frv > 1 overcame the orographic barrier and crossed the peninsula. While, those with Frv < 1 were blocked by the orography. The blocked vortic…
In this paper, the complexities in the relationship between rainfall and sea surface temperature (SST) anomalies during the winter monsoon (November-January) over India were evaluated statistically using scatter plot matrices and autocorrelation functions.Linear as well as polynomial trend equations were obtained and it was observed that the coefficient of determination for the linear trend was very low and it remained low even when polynomial trend of degree six was used. An exponential regression equation and an artificial neural network with extensive variable selection were generated to fo…
We study the role of galactic cosmic ray (GCR) variability in influencing the rainfall variability in Indian Summer Monsoon Rainfall (ISMR) season. We find that on an average during 'drought' (low ISMR) periods in India, GCR flux is decreasing, and during 'flood' (high ISMR) periods, GCR flux is increasing. The results of our analysis suggest for a possibility that the decreasing GCR flux during the summer monsoon season in India may suppress the rainfall. On the other hand, increasing GCR flux may enhance the rainfall. We suspect that in addition to real environmental conditions, significant …
Sub-seasonal Modulation and Predictability of Indian monsoon hourly Rainfall Extremes
Gauhati University（古哈提大学）；Indian Institute of Technology Madras（马德拉斯印度理工学院）；Indian Institute of Tropical Meteorology（印度热带气象研究所）；Cotton University（科顿大学）
Using the Morlet continuous wavelet transform on data over the period 1871-1990, it is found that the global wavelet cross spectra between two solar activity indices and seven major Indian monsoon rainfall time series show significant power around the period of the 11 year solar cycle, passing the $χ^2$ test of significance proposed by Torrence and Compo (1998) at levels exceeding 95% in 10 out of the 14 cases studied. Furthermore two distinct epochs are found in the computed cross-spectrum, the transition between them occurring around the decade 1915-1925, beyond which solar activity paramete…
During 2015, the southwest monsoon (SWM) rainfall over the country remained deficient with seasonal rainfall of about 86% of the long period average (Table 1.1). Last year, the seasonal rainfall deficiency over the country as a whole was 12% (www.imd.gov.in). Thus, this is a fourth episode of two consecutive years, with deficient monsoon, similar to 1904-05, 1965-66 and 1986-87 (www.imd.gov.in).
Scientific basis for long-lead seasonal prediction of Indian summer monsoon rainfall (ISMR) critical for water resource and crop strategy planning is lacking. Using a new predictor discovery method, here we show that the depth of 20 degree isotherm (D20) is least influenced by atmospheric noise and that the 18-month lead forecasts of ISMR have high potential skill (r = 0.86). The high potential predictability is due to smaller initial errors associated with the 18-month lead initial conditions and their slow growth associated with the El Nino and Southern Oscillation (ENSO). The potential skil…
In this diagnostic study we analyze changes of rainfall seasonality and dry spells by the end of the twenty-first century under the most extreme IPCC5 emission scenario (RCP8.5) as projected by twenty-four coupled climate models participating to Coupled Model Intercomparison Project 5. We use estimates of the centroid of the monthly rainfall distribution as an index of the rainfall timing and a threshold-independent, information theory-based quantity such as relative entropy (RE) to quantify the concentration of annual rainfall and the number of dry months and to build a monsoon dimensionless …
The sub-seasonal and synoptic-scale variability of the Indian summer monsoon rainfall are controlled primarily by monsoon intra-seasonal oscillations (MISO) and low pressure systems (LPS), respectively. The positive and negative phases of MISO lead to alternate epochs of above-normal (active) and below-normal (break) spells of rainfall. LPSs are embedded within the different phases of MISO and are known to produce heavy precipitation events over central India. Whether the interaction with the MISO phases modulates the precipitation response of LPSs, and thereby the characteristics of extreme r…
The initiation of the Indian summer monsoon circulation during late May / early June arises through large-scale land-sea thermal contrast and setting up of negative pressure gradient between the Monsoon Trough over the Indo-Gangetic plains and the Mascarene High over the subtropical Indian Ocean. The meridional pressure gradient together with the Earth's rotation (Coriolis force) creates the summer monsoon cross-equatorial flow, while feedbacks between moisture-laden winds and latent heat release from precipitating systems maintain the monsoon circulation during the June-September (JJAS) rainy…
A litany of research has been published claiming strong solar influences on the Earth's weather and climate. Much of this work includes documented errors and false-positives, yet is still frequently used to substantiate arguments of global warming denial. This manuscript reports on a recent study by Badruddin & Aslam (2014), hereafter BA14, which claimed a highly significant ($p=1.4\times10^{-5}$) relationship between extremes in the intensity of the Indian monsoon and the cosmic ray flux. They further speculated that the relationship they observed may apply across the entire tropical and sub-…
The Indian summer monsoon rainfall (ISMR) has a decisive influence on India's agricultural output and economy. Extreme deviations from the normal seasonal amount of rainfall can cause severe droughts or floods, affecting Indian food production and security. Despite the development of sophisticated statistical and dynamical climate models, a long-term and reliable prediction of the ISMR has remained a challenging problem. Towards achieving this goal, here we construct a series of dynamical and physical climate networks based on the global near surface air temperature field. We uncover that some…
Skilful prediction of the seasonal Indian summer monsoon (ISM) rainfall (ISMR) at least one season in advance has great socio-economic value. It represents a lifeline for about a sixth of the world's population. The ISMR prediction remained a challenging problem with the sub-critical skills of the dynamical models attributable to limited understanding of the interaction among clouds, convection, and circulation. The variability of cloud hydrometeors (cloud ice and cloud water) in different time scales (3-7 days, 10-20 days and 30-60 days bands) are examined from re-analysis data during Indian …
Increasing greenhouse gases will change many aspects of the Earth's climate, from its annual mean to the frequency of extremes such as heat waves and droughts. Here we report that the current generation of climate models predicts a delay in the seasonal cycle of global rainfall and ocean temperature in response to increasing greenhouse gases, with important implications for the regional monsoons. In particular, the rainy season of the semi-arid African Sahel is projected to start later and become shorter: an undesirable change for local rainfed agriculture and pastoralism. Previous work has hi…
Large socio-economic impact of the Indian Summer Monsoon (ISM) extremes motivated numerous attempts at its long range prediction over the past century. However, a rather estimated low potential predictability limit (PPL) of seasonal prediction of the ISM, contributed significantly by 'internal' interannual variability was considered insurmountable. Here we show that the 'internal' variability contributed by the ISM sub-seasonal (synoptic + intra-seasonal) fluctuations, so far considered chaotic, is partly predictable as found to be tied to slowly varying forcing (e.g. El Nino and Southern Osci…
This study assesses a Continuous Data Assimilation (CDA) dynamical-downscaling algorithm for enhancing the simulation of the Indian summer monsoon (ISM) system. CDA is a mathematically rigorous technique that has been recently introduced to constrain the large-scale features of high-resolution atmospheric models with coarse spatial scale data. It is similar to spectral nudging but does not require any spectral decomposition for scales separation. This is expected to be particularly relevant for ISM, which involves various interactions between large-scale circulations and regional physical proc…
The correlation between increased Sahel rainfall and reduced Saharan surface pressure is well established in observations and global climate models, and has been used to imply that increased Sahel rainfall is caused by a stronger shallow meridional circulation (SMC) over the Sahara. This study uses two atmospheric reanalyses to examine interannual variability of Sahel rainfall and the Saharan SMC, which consists of northward near-surface flow across the Sahel into the Sahara and southward flow near 700 hPa out of the Sahara. During wet Sahel years, the Saharan SMC shifts poleward, producing a …
The forecast of Indian monsoon droughts has been predicated on the notion of a season-long rainfall deficit linked to warm anomalies in the equatorial Pacific. Here, we show that in fact nearly half of all droughts over the past century were sub-seasonal, and characterized by an abrupt decline in late-season rainfall. Furthermore, the potential driver of this class of droughts is a coherent cold anomaly in the North Atlantic Ocean. The vorticity forcing associated with this oceanic marker extends through the depth of the troposphere, and results in a wavetrain which curves towards the equator …
Massive river interlinking projects are proposed to offset observed increasing trends of extremes, such as droughts and floods in India, the second highest populated country.These river interlinking projects involve water transfer from surplus to deficit river basins through reservoirs and canals, but without an in-depth understanding of the hydro-meteorological consequences. Using information theory-based causal delineation techniques, a coupled regional climate model, and multiple reanalysis datasets, we show that causal pathways exist across different basins in India due to strong land-atmo…
The identification of regions of similar climatological behavior can be utilized for the discovery of spatial relationships over long-range scales, including teleconnections. In this regard, the global picture of the interdependence patterns of extreme rainfall events (EREs) still needs to be further explored. To this end, we propose a top-down complex-network-based clustering workflow, with the combination of consensus clustering and mutual correspondences. Consensus clustering provides a reliable community structure under each dataset, while mutual correspondences build a matching relationsh…
Did recent sea surface temperature warming reinforce the extreme East Asian summer monsoon precipitation in 2020?
Ulsan National Institute of Science and Technology（蔚山科学技术院）；Pohang University of Science and Technology（浦项科技大学）；Yonsei University（延世大学）；Seoul National University（首尔大学）
Evaluation of High-Resolution Gridded Precipitation Datasets Against a Dense Rain Gauge Network During the Indian Summer Monsoon
Indian Institute of Technology (IIT) Madras（印度理工学院马德拉斯分校）；CSIR National Institute of Data Science and Artificial Intelligence（印度科学、技术和医学研究理事会数据科学与人工智能国家研究所）；IIT Delhi（印度理工学院德里分校）
We analyse Indian summer monsoon (ISM) seasonal reforecasts by CFSv2 model, initiated from January (4-month lead time, L4) through May (0-month lead time, L0) initial conditions (ICs), to examine the cause for highest all-India ISM rainfall (ISMR) forecast skill with February (L3) ICs. The reported highest L3 skill is based on correlation between observed and predicted interannual variation (IAV) of ISMR. Other scores such as mean error, bias, RMSE, mean, standard deviation and coefficient of variation, indicate higher or comparable skill for April(L1)/May(L0) ICs. Though theory suggests that …
Accurate short range weather forecasting has significant implications for various sectors. Machine learning based approaches, e.g., deep learning, have gained popularity in this domain where the existing numerical weather prediction (NWP) models still have modest skill after a few days. Here we use a ConvLSTM network to develop a deep learning model for precipitation forecasting. The crux of the idea is to develop a forecasting model which involves convolution based feature selection and uses long term memory in the meteorological fields in conjunction with gradient based learning algorithm. P…
Default values for many model parameters in Numerical Weather Prediction models are typically adopted based on theoretical or experimental investigations by scheme designers. Short-range forecasts are substantially affected by the specification of parameters in the Weather Research and Forecasting (WRF) model. The presence of a multitude of parameters and several output variables in the WRF model renders appropriate parameter value identification quite challenging. The objective of the current study is to reduce the uncertainty in the model outcomes through the recognition of parameters that s…
$ $From June--September, the summer monsoon current (SMC) flows eastward south of Sri Lanka and bends northeastward to form a swift jet that enters the Bay of Bengal (BoB). As such, it is a crucial part of the water exchange between the Arabian Sea (AS) and BoB. The processes that determine the evolution, intensification and meandering of the SMC are only partly understood. They involve both local and remote forcing by the wind, as well as interactions with westward-propagating Rossby waves and eddies. In this study, we investigate these processes using an Indian-Ocean general circulation mode…
Accumulated precipitation forecasts are of high socioeconomic importance for agriculturally dominated societies in northern tropical Africa. In this study, we analyze the performance of nine operational global ensemble prediction systems (EPSs) relative to climatology-based forecasts for 1 to 5-day accumulated precipitation based on the monsoon seasons 2007-2014 for three regions within northern tropical Africa. To assess the full potential of raw ensemble forecasts across spatial scales, we apply state-of-the-art statistical postprocessing methods in form of Bayesian Model Averaging (BMA) and…
In order to study the relation between the components of atmospheric circulation and summer precipitation over the Iranian plateau, daily rainfall data of synoptic stations of Iran were obtained from IRIMO for the period 1970 to 2003. Composite maps of different components such as pressure levels, vector wind, U and V winds, vertical velocity, Specific humidity, OLR, streamlines, vorticity, and the temperature was drawn and analyzed. The results showed that the summer circulation of the atmosphere over South West Asia after a sudden change from late May to early June was established in its nor…
The Yangtze River has been subject to heavy flooding throughout history, and in recent times severe floods such as those in 1998 have resulted in heavy loss of life and livelihoods. Dams along the river help to manage flood waters, and are important sources of electricity for the region. Being able to forecast high-impact events at long lead times therefore has enormous potential benefit. Recent improvements in seasonal forecasting mean that dynamical climate models can start to be used directly for operational services. The teleconnection from El Niño to Yangtze River basin rainfall meant tha…
This study presents the first systematic comparison of the (thermo-)dynamics associated with all major tropical wave types causing rainfall modulation over northern tropical Africa: Madden Julian Oscillation (MJO), Equatorial Rossby waves (ERs), mixed Rossby-gravity waves (MRGs), Kelvin waves, tropical disturbances (TDs, including African Easterly Waves), and eastward inertio-gravity waves (EIGs). Reanalysis and radiosonde data were analyzed for the period 1981--2013 based on space-time filtering of outgoing longwave radiation. The identified circulation patterns are largely consistent with th…
Divecha Centre for Climate Change（迪韦查气候变化中心）；Indian Institute of Science（印度科学学院）
A univariate time series with high variability can pose a challenge even to Deep Neural Network (DNN). To overcome this, a univariate time series is decomposed into simpler constituent series, whose sum equals the original series. As demonstrated in this article, the conventional one-time decomposition technique suffers from a leak of information from the future, referred to as a data leak. In this work, a novel Moving Front (MF) method is proposed to prevent data leakage, so that the decomposed series can be treated like other time series. Indian Summer Monsoon Rainfall (ISMR) is a very compl…
Low-latitude rainfall variability on the daily to intraseasonal timescale is often related to tropical waves, including convectively coupled equatorial waves, the Madden-Julian Oscillation (MJO), and tropical disturbances. Despite the importance of rainfall variability for vulnerable societies in tropical Africa, the relative influence of tropical waves for this region is largely unknown. This article presents the first systematic comparison of the impact of six wave types on precipitation over northern tropical Africa during the transition and full monsoon seasons, using two satellite product…
Two new indicators of rainfall seasonality based on information entropy, the relative entropy (RE) and the dimensionless seasonality index (DSI), together with the mean annual rainfall, are evaluated on a global scale for recently updated precipitation gridded datasets and for historical simulations from coupled atmosphere-ocean general circulation models. The RE provides a measure of the number of wet months and, for precipitation regimes featuring one maximum in the monthly rain distribution, it is related to the duration of the wet season. The DSI combines the rainfall intensity with its de…
